ClawSec Feed - AI代理安全通告订阅源，实时监控CVE漏洞威胁情报

clawsec-feed by prompt-security/clawsec

144 周安装量

883 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/prompt-security/clawsec --skill clawsec-feed

自动化监控安全

🇨🇳中文介绍

ClawSec Feed 📡

面向 AI 代理的安全通告订阅源监控。订阅社区驱动的威胁情报，及时了解新出现的威胁。

此订阅源每天自动从 NIST 国家漏洞数据库 (NVD) 更新与 OpenClaw、clawdbot 和 Moltbot 相关的 CVE。

由 Prompt Security 开发的开源项目

安装选项

您可以通过两种方式获取 clawsec-feed：

选项 A：与 ClawSec 套件捆绑安装（推荐）

如果您已经安装了 clawsec-suite，您可能已经拥有此功能！

ClawSec-feed 与 ClawSec 套件捆绑在一起，以提供关键的 CVE 和威胁情报信息。当您安装该套件时，如果您尚未安装此订阅源，它将从捆绑的副本中部署。

优势：

方便 - 无需单独下载
标准位置 - 安装到 ~/.openclaw/skills/clawsec-feed/
保留 - 如果您已经安装了订阅源，它不会被覆盖
单一验证 - 作为套件包的一部分进行完整性检查

选项 B：独立安装（本页面）

独立安装 clawsec-feed，无需完整套件。

何时使用独立安装：

您只需要安全通告订阅源（不需要其他套件组件）
您想在安装套件之前安装订阅源
您希望对订阅源安装过程有明确的控制权

优势：

安装更轻量
独立于套件
直接控制安装过程

继续阅读以下内容以获取独立安装说明。

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

步骤 1：创建技能目录并保存此文件

mkdir -p ~/.openclaw/skills/clawsec-feed
# 将本 SKILL.md 文件保存为上述目录中的 SKILL.md

步骤 2：安装技能文件

# 使用重试逻辑获取最新发布标签
LATEST_TAG=$(curl -sSL --retry 3 --retry-delay 1 \
  https://api.github.com/repos/prompt-security/ClawSec/releases | \
  jq -r '[.[] | select(.tag_name | startswith("clawsec-feed-v"))][0].tag_name')

BASE_URL="https://github.com/prompt-security/clawsec/releases/download/$LATEST_TAG"
INSTALL_DIR="${CLAWSEC_INSTALL_DIR:-$HOME/.openclaw/skills/clawsec-feed}"
TEMP_DIR=$(mktemp -d)
trap "rm -rf '$TEMP_DIR'" EXIT

# 下载 checksums.json（完整性验证必需）
echo "正在下载校验和..."
if ! curl -sSL --fail --show-error --retry 3 --retry-delay 1 \
     "$BASE_URL/checksums.json" -o "$TEMP_DIR/checksums.json"; then
  echo "错误：无法下载 checksums.json"
  exit 1
fi

# 验证 checksums.json 结构
if ! jq -e '.skill and .version and .files' "$TEMP_DIR/checksums.json" >/dev/null 2>&1; then
  echo "错误：checksums.json 结构无效"
  exit 1
fi

# 主要方式：尝试 .skill 工件
echo "正在尝试 .skill 工件安装..."
if curl -sSL --fail --show-error --retry 3 --retry-delay 1 \
   "$BASE_URL/clawsec-feed.skill" -o "$TEMP_DIR/clawsec-feed.skill" 2>/dev/null; then

  # 安全性：检查工件大小（防止 DoS）
  ARTIFACT_SIZE=$(stat -c%s "$TEMP_DIR/clawsec-feed.skill" 2>/dev/null || stat -f%z "$TEMP_DIR/clawsec-feed.skill")
  MAX_SIZE=$((50 * 1024 * 1024))  # 50MB

  if [ "$ARTIFACT_SIZE" -gt "$MAX_SIZE" ]; then
    echo "警告：工件过大 ($(( ARTIFACT_SIZE / 1024 / 1024 ))MB)，回退到单独文件方式"
  else
    echo "正在解压工件 ($(( ARTIFACT_SIZE / 1024 ))KB)..."

    # 安全性：解压前检查路径遍历
    if unzip -l "$TEMP_DIR/clawsec-feed.skill" | grep -qE '\.\./|^/|~/'; then
      echo "错误：在工件中检测到路径遍历 - 可能存在安全问题！"
      exit 1
    fi

    # 安全性：检查文件数量（防止 zip 炸弹）
    FILE_COUNT=$(unzip -l "$TEMP_DIR/clawsec-feed.skill" | grep -c "^[[:space:]]*[0-9]" || echo 0)
    if [ "$FILE_COUNT" -gt 100 ]; then
      echo "错误：工件包含文件过多 ($FILE_COUNT) - 可能是 zip 炸弹"
      exit 1
    fi

    # 解压到临时目录
    unzip -q "$TEMP_DIR/clawsec-feed.skill" -d "$TEMP_DIR/extracted"

    # 验证 skill.json 是否存在
    if [ ! -f "$TEMP_DIR/extracted/clawsec-feed/skill.json" ]; then
      echo "错误：在工件中未找到 skill.json"
      exit 1
    fi

    # 验证所有解压文件的校验和
    echo "正在验证校验和..."
    CHECKSUM_FAILED=0
    for file in $(jq -r '.files | keys[]' "$TEMP_DIR/checksums.json"); do
      EXPECTED=$(jq -r --arg f "$file" '.files[$f].sha256' "$TEMP_DIR/checksums.json")
      FILE_PATH=$(jq -r --arg f "$file" '.files[$f].path' "$TEMP_DIR/checksums.json")

      # 先尝试嵌套路径，然后是扁平文件名
      if [ -f "$TEMP_DIR/extracted/clawsec-feed/$FILE_PATH" ]; then
        ACTUAL=$(shasum -a 256 "$TEMP_DIR/extracted/clawsec-feed/$FILE_PATH" | cut -d' ' -f1)
      elif [ -f "$TEMP_DIR/extracted/clawsec-feed/$file" ]; then
        ACTUAL=$(shasum -a 256 "$TEMP_DIR/extracted/clawsec-feed/$file" | cut -d' ' -f1)
      else
        echo "  ✗ $file (在工件中未找到)"
        CHECKSUM_FAILED=1
        continue
      fi

      if [ "$EXPECTED" != "$ACTUAL" ]; then
        echo "  ✗ $file (校验和不匹配)"
        CHECKSUM_FAILED=1
      else
        echo "  ✓ $file"
      fi
    done

    if [ "$CHECKSUM_FAILED" -eq 0 ]; then
      # 验证 feed.json 结构（技能特定）
      if [ -f "$TEMP_DIR/extracted/clawsec-feed/advisories/feed.json" ]; then
        FEED_FILE="$TEMP_DIR/extracted/clawsec-feed/advisories/feed.json"
      elif [ -f "$TEMP_DIR/extracted/clawsec-feed/feed.json" ]; then
        FEED_FILE="$TEMP_DIR/extracted/clawsec-feed/feed.json"
      else
        echo "错误：在工件中未找到 feed.json"
        exit 1
      fi

      if ! jq -e '.version and .advisories' "$FEED_FILE" >/dev/null 2>&1; then
        echo "错误：feed.json 缺少必需字段 (version, advisories)"
        exit 1
      fi

      # 成功：从工件安装
      echo "正在从工件安装..."
      mkdir -p "$INSTALL_DIR"
      cp -r "$TEMP_DIR/extracted/clawsec-feed"/* "$INSTALL_DIR/"
      chmod 600 "$INSTALL_DIR/skill.json"
      find "$INSTALL_DIR" -type f ! -name "skill.json" -exec chmod 644 {} \;
      echo "成功：技能已从 .skill 工件安装"
      exit 0
    else
      echo "警告：校验和验证失败，回退到单独文件方式"
    fi
  fi
fi

# 回退方式：下载单独文件
echo "正在从 checksums.json 清单下载单独文件..."
mkdir -p "$TEMP_DIR/downloads"

DOWNLOAD_FAILED=0
for file in $(jq -r '.files | keys[]' "$TEMP_DIR/checksums.json"); do
  FILE_URL=$(jq -r --arg f "$file" '.files[$f].url' "$TEMP_DIR/checksums.json")
  EXPECTED=$(jq -r --arg f "$file" '.files[$f].sha256' "$TEMP_DIR/checksums.json")

  echo "正在下载: $file"
  if ! curl -sSL --fail --show-error --retry 3 --retry-delay 1 \
       "$FILE_URL" -o "$TEMP_DIR/downloads/$file"; then
    echo "错误：无法下载 $file"
    DOWNLOAD_FAILED=1
    continue
  fi

  # 立即验证校验和
  ACTUAL=$(shasum -a 256 "$TEMP_DIR/downloads/$file" | cut -d' ' -f1)
  if [ "$EXPECTED" != "$ACTUAL" ]; then
    echo "错误：$file 的校验和不匹配"
    DOWNLOAD_FAILED=1
  else
    echo "  ✓ 已验证: $file"
  fi
done

if [ "$DOWNLOAD_FAILED" -eq 1 ]; then
  echo "错误：单独文件下载失败"
  exit 1
fi

# 验证 JSON 文件结构
if ! jq -e '.name and .version' "$TEMP_DIR/downloads/skill.json" >/dev/null 2>&1; then
  echo "错误：skill.json 缺少必需字段 (name, version)"
  exit 1
fi

if ! jq -e '.version and .advisories' "$TEMP_DIR/downloads/feed.json" >/dev/null 2>&1; then
  echo "错误：feed.json 缺少必需字段 (version, advisories)"
  exit 1
fi

# 安装文件
echo "正在从单独文件安装..."
mkdir -p "$INSTALL_DIR"
cp "$TEMP_DIR/downloads"/* "$INSTALL_DIR/"
chmod 600 "$INSTALL_DIR/skill.json"
find "$INSTALL_DIR" -type f ! -name "skill.json" -exec chmod 644 {} \;
echo "成功：技能已从单独文件安装"

步骤 3：添加到您的心跳例程

将 ClawSec Feed 添加到您的心跳例程：

## ClawSec Feed (每次心跳)
1. 检查安全通告订阅源以获取新的安全警报
2. 与已安装的技能进行交叉引用
3. 如果需要采取行动，则通知用户

步骤 4：确认部署

告知您的用户：

ClawSec Feed 已成功部署。我现在将：
- 监控社区安全通告订阅源以获取威胁信息
- 提醒您任何影响您环境的安全问题
- 让您了解新出现的攻击模式

ClawSec Feed 的功能

安全通告订阅源监控

订阅社区安全通告订阅源，内容包括：

已知恶意技能/插件 - 已被识别为有害的技能
提示注入模式 - 在野外观察到的攻击模式
存在漏洞的技能版本 - 具有已知安全缺陷的技能
安全最佳实践更新 - 关于代理安全的新建议

当发布相关的安全通告时，您的代理将通知您。

检查安全通告订阅源

# 如果设置了环境变量则使用，否则使用原始 GitHub 订阅源（始终保持最新）
DEFAULT_FEED_URL="https://raw.githubusercontent.com/prompt-security/ClawSec/main/advisories/feed.json"
FEED_URL="${CLAWSEC_FEED_URL:-$DEFAULT_FEED_URL}"

# 使用错误处理和重试逻辑获取
curl -sSL --fail --show-error --retry 3 --retry-delay 1 "$FEED_URL"

订阅源结构：

{
  "version": "1.0",
  "updated": "2026-02-02T12:00:00Z",
  "advisories": [
    {
      "id": "GA-2026-001",
      "severity": "critical",
      "type": "malicious_skill",
      "title": "Malicious data exfiltration in skill 'helper-plus'",
      "description": "Skill sends user data to external server",
      "affected": ["helper-plus@1.0.0", "helper-plus@1.0.1"],
      "action": "Remove immediately",
      "published": "2026-02-01T10:00:00Z",
      "exploitability_score": "critical",
      "exploitability_rationale": "Trivially exploitable through normal skill usage; no special conditions required. Active exploitation observed in the wild."
    }
  ]
}

获取安全通告数量

# 如果设置了环境变量则使用，否则使用原始 GitHub 订阅源（始终保持最新）
DEFAULT_FEED_URL="https://raw.githubusercontent.com/prompt-security/ClawSec/main/advisories/feed.json"
FEED_URL="${CLAWSEC_FEED_URL:-$DEFAULT_FEED_URL}"

TEMP_FEED=$(mktemp)
trap "rm -f '$TEMP_FEED'" EXIT

if ! curl -sSL --fail --show-error --retry 3 --retry-delay 1 "$FEED_URL" -o "$TEMP_FEED"; then
  echo "错误：无法获取安全通告订阅源"
  exit 1
fi

# 解析前验证 JSON
if ! jq empty "$TEMP_FEED" 2>/dev/null; then
  echo "错误：订阅源中的 JSON 无效"
  exit 1
fi

FEED=$(cat "$TEMP_FEED")

# 使用错误处理获取安全通告数量
COUNT=$(echo "$FEED" | jq '.advisories | length')
if [ $? -ne 0 ]; then
  echo "错误：无法解析安全通告"
  exit 1
fi
echo "安全通告数量: $COUNT"

获取严重安全通告

# 使用 jq 错误处理解析严重安全通告
CRITICAL=$(echo "$FEED" | jq '.advisories[] | select(.severity == "critical")')
if [ $? -ne 0 ]; then
  echo "错误：无法筛选严重安全通告"
  exit 1
fi
echo "$CRITICAL"

获取过去 7 天的安全通告

# 使用 UTC 时区以确保日期处理一致
WEEK_AGO=$(TZ=UTC date -v-7d +%Y-%m-%dT00:00:00Z 2>/dev/null || TZ=UTC date -d '7 days ago' +%Y-%m-%dT00:00:00Z)
RECENT=$(echo "$FEED" | jq --arg since "$WEEK_AGO" '.advisories[] | select(.published > $since)')
if [ $? -ne 0 ]; then
  echo "错误：无法筛选近期安全通告"
  exit 1
fi
echo "$RECENT"

按可利用性评分筛选

共享的可利用性优先级指导原则维护在：

获取安全通告的可利用性上下文

# 显示特定 CVE 的可利用性详情
CVE_ID="CVE-2026-27488"
echo "$FEED" | jq --arg cve "$CVE_ID" '.advisories[] | select(.id == $cve) | {
  id: .id,
  severity: .severity,
  exploitability_score: .exploitability_score,
  exploitability_rationale: .exploitability_rationale,
  title: .title
}'

按可利用性对安全通告进行优先级排序

# 按可利用性对安全通告排序（严重 → 高 → 中 → 低）
# 这有助于代理专注于最需要立即采取行动的威胁
echo "$FEED" | jq '[.advisories[] | select(.exploitability_score != null)] |
  sort_by(
    if .exploitability_score == "critical" then 0
    elif .exploitability_score == "high" then 1
    elif .exploitability_score == "medium" then 2
    elif .exploitability_score == "low" then 3
    else 4 end
  )'

交叉引用已安装的技能

检查您已安装的技能是否受到安全通告的影响：

# 列出您已安装的技能（根据您的平台调整路径）
INSTALL_DIR="${CLAWSEC_INSTALL_DIR:-$HOME/.openclaw/skills}"

# 如果设置了环境变量则使用，否则使用原始 GitHub 订阅源（始终保持最新）
DEFAULT_FEED_URL="https://raw.githubusercontent.com/prompt-security/ClawSec/main/advisories/feed.json"
FEED_URL="${CLAWSEC_FEED_URL:-$DEFAULT_FEED_URL}"

TEMP_FEED=$(mktemp)
trap "rm -f '$TEMP_FEED'" EXIT

if ! curl -sSL --fail --show-error --retry 3 --retry-delay 1 "$FEED_URL" -o "$TEMP_FEED"; then
  echo "错误：无法获取安全通告订阅源"
  exit 1
fi

# 验证并解析订阅源
if ! jq empty "$TEMP_FEED" 2>/dev/null; then
  echo "错误：订阅源中的 JSON 无效"
  exit 1
fi

FEED=$(cat "$TEMP_FEED")
AFFECTED=$(echo "$FEED" | jq -r '.advisories[].affected[]?' 2>/dev/null | sort -u)
if [ $? -ne 0 ]; then
  echo "错误：无法从订阅源解析受影响的技能"
  exit 1
fi

# 在处理前安全地验证所有已安装的技能
# 这可以防止通过恶意文件名进行 shell 注入
VALIDATED_SKILLS=()
while IFS= read -r -d '' skill_path; do
  skill=$(basename "$skill_path")

  # 在添加到数组前验证技能名称（防止注入）
  if [[ "$skill" =~ ^[a-zA-Z0-9_-]+$ ]]; then
    VALIDATED_SKILLS+=("$skill")
  else
    echo "警告：跳过无效的技能名称: $skill" >&2
  fi
done < <(find "$INSTALL_DIR" -mindepth 1 -maxdepth 1 -type d -print0 2>/dev/null)

# 针对受影响列表检查每个已验证的技能
# 使用 grep -qF 进行固定字符串匹配（防止正则表达式注入）
for skill in "${VALIDATED_SKILLS[@]}"; do
  # 此时，$skill 保证匹配 ^[a-zA-Z0-9_-]+$
  if echo "$AFFECTED" | grep -qF "$skill"; then
    echo "警告：已安装的技能 '$skill' 存在安全通告！"
    # 获取此技能的安全通告详情
    echo "$FEED" | jq --arg s "$skill" '.advisories[] | select(.affected[] | contains($s))'
  fi
done

如果发现受影响的技能：

检查安全通告的详情和严重性
对于严重/高严重性，立即通知您的用户
包含安全通告中推荐的操作

类型	描述
`malicious_skill`	被识别为故意有害的技能
`vulnerable_skill`	存在安全漏洞的技能
`prompt_injection`	已知的提示注入模式
`attack_pattern`	观察到的攻击技术
`best_practice`	安全建议

严重性	所需操作
`critical`	立即通知用户，采取行动
`high`	尽快通知用户，计划修复
`medium`	在下一次交互时通知
`low`	记录以供参考

优先处理高可利用性威胁

重要提示： 在审查安全通告时，除了严重性之外，始终要按可利用性评分进行优先级排序。可利用性评分表明漏洞在实践中被利用的难易程度，帮助您专注于最需要采取行动的威胁。

可利用性优先级等级

可利用性	含义	操作优先级
`high`	可轻易或容易地利用，且有公开工具	立即通知
`medium`	可利用但需要特定条件	标准通知
`low`	难以利用或仅为理论性	低优先级通知

如何在通知中使用可利用性

首先筛选高可利用性：

# 获取高可利用性安全通告
echo "$FEED" | jq '.advisories[] | select(.exploitability_score == "high")'

在通知中包含可利用性：

📡 ClawSec Feed：高可利用性警报

严重 - CVE-2026-27488 (可利用性：高)
  → skill-loader v2.1.0 中可轻易利用的 RCE
  → 公开的漏洞利用代码可用
  → 推荐操作：立即移除或升级到 v2.1.1

按严重性和可利用性进行优先级排序：
- 高严重性 + 高可利用性的 CVE 比严重严重性 + 低可利用性的 CVE 更紧急
- 将用户的注意力集中在既严重又容易被利用的威胁上
- 包含可利用性理由，以帮助用户理解风险背景

通知优先级顺序示例

当存在多个安全通告时，按以下顺序呈现：

严重严重性 + 高可利用性 - 最紧急
高严重性 + 高可利用性
严重严重性 + 中/低可利用性
高严重性 + 中/低可利用性
中/低严重性（任何可利用性）

这确保您首先向用户提醒最需要采取行动、立即危险的威胁。

何时通知您的用户

立即通知（严重）：

影响已安装技能的新严重安全通告
检测到主动利用
高可利用性评分（无论严重性如何）

尽快通知（高）：

影响已安装技能的新高严重性安全通告
无法获取安全通告订阅源（网络问题？）
高严重性且中等可利用性

在下一次交互时通知（中）：

新的中等严重性安全通告
一般安全更新
低可利用性安全通告

仅记录（低/信息）：

低严重性安全通告（如果用户询问则提及）
已检查订阅源，无新安全通告
理论性漏洞（低可利用性，低严重性）

如果有新的安全通告：

📡 ClawSec Feed：自上次检查后有 2 个新安全通告

严重 - GA-2026-015：恶意提示模式 "ignore-all" (可利用性：高)
  → 检测到提示注入技术。更新您的系统提示防御。
  → 可利用性：使用公开记录的技术可轻易利用。

高 - GA-2026-016：存在漏洞的技能 "data-helper" v1.2.0 (可利用性：中)
  → 您已安装此技能！推荐操作：更新到 v1.2.1 或移除。
  → 可利用性：需要特定配置；不易利用。

如果没有新内容：

订阅源正常 - 已检查安全通告订阅源，无新警报。📡

跟踪上次订阅源检查以识别新的安全通告：

{
  "schema_version": "1.0",
  "last_feed_check": "2026-02-02T15:00:00Z",
  "last_feed_updated": "2026-02-02T12:00:00Z",
  "known_advisories": ["GA-2026-001", "GA-2026-002"]
}

保存到：~/.openclaw/clawsec-feed-state.json

STATE_FILE="$HOME/.openclaw/clawsec-feed-state.json"

# 如果状态文件不存在，则创建并设置安全权限
if [ ! -f "$STATE_FILE" ]; then
  echo '{"schema_version":"1.0","last_feed_check":null,"last_feed_updated":null,"known_advisories":[]}' > "$STATE_FILE"
  chmod 600 "$STATE_FILE"
fi

# 读取前验证状态文件
if ! jq -e '.schema_version' "$STATE_FILE" >/dev/null 2>&1; then
  echo "警告：状态文件损坏或模式无效。正在创建备份并重置。"
  cp "$STATE_FILE" "${STATE_FILE}.bak.$(TZ=UTC date +%Y%m%d%H%M%S)"
  echo '{"schema_version":"1.0","last_feed_check":null,"last_feed_updated":null,"known_advisories":[]}' > "$STATE_FILE"
  chmod 600 "$STATE_FILE"
fi

# 检查主要版本兼容性
SCHEMA_VER=$(jq -r '.schema_version // "0"' "$STATE_FILE")
if [[ "${SCHEMA_VER%%.*}" != "1" ]]; then
  echo "警告：状态文件模式版本 $SCHEMA_VER 可能与此版本不兼容"
fi

# 更新上次检查时间（始终使用 UTC）
TEMP_STATE=$(mktemp)
if jq --arg t "$(TZ=UTC date +%Y-%m-%dT%H:%M:%SZ)" '.last_feed_check = $t' "$STATE_FILE" > "$TEMP_STATE"; then
  mv "$TEMP_STATE" "$STATE_FILE"
  chmod 600 "$STATE_FILE"
else
  echo "错误：无法更新状态文件"
  rm -f "$TEMP_STATE"
fi

重要提示： 为避免对订阅源服务器发出过多请求，请遵循以下指南：

检查类型	推荐间隔	最小间隔
心跳检查	每 15-30 分钟	5 分钟
完整订阅源刷新	每 1-4 小时	30 分钟
交叉引用扫描	每次会话一次	5 分钟

# 检查自上次检查以来是否已过去足够的时间
STATE_FILE="$HOME/.openclaw/clawsec-feed-state.json"
MIN_INTERVAL_SECONDS=300  # 5 分钟

LAST_CHECK=$(jq -r '.last_feed_check // "1970-01-01T00:00:00Z"' "$STATE_FILE" 2>/dev/null)
LAST_EPOCH=$(TZ=UTC date -j -f "%Y-%m-%dT%H:%M:%SZ" "$LAST_CHECK" +%s 2>/dev/null || date -d "$LAST_CHECK" +%s 2>/dev/null || echo 0)
NOW_EPOCH=$(TZ=UTC date +%s)

if [ $((NOW_EPOCH - LAST_EPOCH)) -lt $MIN_INTERVAL_SECONDS ]; then
  echo "速率限制：上次检查是在不到 5 分钟前。跳过。"
  exit 0
fi

环境变量（可选）

变量	描述	默认值
`CLAWSEC_FEED_URL`	自定义安全通告订阅源 URL	原始 GitHub (`main` 分支)
`CLAWSEC_INSTALL_DIR`	安装目录	`~/.openclaw/skills/clawsec-feed`

检查并安装新版本：

# 检查当前安装的版本
INSTALL_DIR="${CLAWSEC_INSTALL_DIR:-$HOME/.openclaw/skills/clawsec-feed}"
CURRENT_VERSION=$(jq -r '.version' "$INSTALL_DIR/skill.json" 2>/dev/null || echo "unknown")
echo "已安装版本: $CURRENT_VERSION"

# 检查最新可用版本
LATEST_URL="https://api.github.com/repos/prompt-security/ClawSec/releases"
LATEST_VERSION=$(curl -sSL --fail --show-error --retry 3 --retry-delay 1 "$LATEST_URL" 2>/dev/null | \
  jq -r '[.[] | select(.tag_name | startswith("clawsec-feed-v"))][0].tag_name // empty' | \
  sed 's/clawsec-feed-v//')

if [ -z "$LATEST_VERSION" ]; then
  echo "警告：无法确定最新版本"
else
  echo "最新版本: $LATEST_VERSION"

  if [ "$CURRENT_VERSION" != "$LATEST_VERSION" ]; then
    echo "有可用更新！请使用新版本运行部署步骤。"
  else
    echo "您正在运行最新版本。"
  fi
fi

初始下载完整性

引导信任问题： 此技能的初始下载无法由技能本身验证。要建立信任：

验证源 URL - 确保您是从 https://clawsec.prompt.security 下载
检查发布签名 - GitHub 签署我们的发布；验证发布来自校验和。
比较校验和 - 下载后，将 SHA-256 哈希值与发布的 checksums.json 进行比较：

# 下载 SKILL.md 后，验证其完整性

EXPECTED_HASH="<hash-from-checksums.json>"
ACTUAL_HASH=$(shasum -a 256 SKILL.md | cut -d' ' -f1)

if [ "$EXPECTED_HASH" != "$ACTUAL_HASH" ]; then
  echo "错误：技能文件完整性检查失败！"
  echo "此文件可能已被篡改。请勿继续。"
  exit 1
fi

注意： 为了最大程度的安全性，请通过单独的受信任渠道验证 checksums.json（例如，直接从 GitHub 发布页面 UI，而不是通过 curl）。

openclaw-audit-watchdog - 自动化的每日安全审计
clawtributor - 向社区报告漏洞

GNU AGPL v3.0 或更高版本 - 详情请参阅仓库。

由 Prompt Security 团队和代理社区使用 📡 构建。

🇺🇸English

ClawSec Feed 📡

Security advisory feed monitoring for AI agents. Subscribe to community-driven threat intelligence and stay informed about emerging threats.

This feed is automatically updated daily with CVEs related to OpenClaw, clawdbot, and Moltbot from the NIST National Vulnerability Database (NVD).

An open source project byPrompt Security

Installation Options

You can get clawsec-feed in two ways:

Option A: Bundled with ClawSec Suite (Recommended)

If you've installed clawsec-suite, you may already have this!

ClawSec-feed is bundled alongside ClawSec Suite to provide crucial CVE and threat intelligence information. When you install the suite, if you don't already have the feed installed, it will be deployed from the bundled copy.

Advantages:

Convenient - no separate download needed
Standard location - installed to ~/.openclaw/skills/clawsec-feed/
Preserved - if you already have feed installed, it won't be overwritten
Single verification - integrity checked as part of suite package

Option B: Standalone Installation (This Page)

Install clawsec-feed independently without the full suite.

When to use standalone:

You only need the advisory feed (not other suite components)
You want to install before installing the suite
You prefer explicit control over feed installation

Advantages:

Lighter weight installation
Independent from suite
Direct control over installation process

Continue below for standalone installation instructions.

Installation Steps: Agents should review scripts before execution!

# Get latest clawsec-feed release tag
LATEST_TAG=$(curl -sSL https://api.github.com/repos/prompt-security/ClawSec/releases | \
  jq -r '[.[] | select(.tag_name | startswith("clawsec-feed-v"))][0].tag_name')

# Download SKILL.md from latest release
SKILL_URL="https://github.com/prompt-security/clawsec/releases/download/$LATEST_TAG/SKILL.md"
curl -sSL --fail --show-error "$SKILL_URL"

Once you have this skill file, proceed to Deploy ClawSec Feed below.

Deploy ClawSec Feed

Installation steps:

Step 1: Create skill directory and save this file

mkdir -p ~/.openclaw/skills/clawsec-feed
# Save this SKILL.md as SKILL.md in the directory above

Step 2: Install skill files

# Get latest release tag with retry logic
LATEST_TAG=$(curl -sSL --retry 3 --retry-delay 1 \
  https://api.github.com/repos/prompt-security/ClawSec/releases | \
  jq -r '[.[] | select(.tag_name | startswith("clawsec-feed-v"))][0].tag_name')

BASE_URL="https://github.com/prompt-security/clawsec/releases/download/$LATEST_TAG"
INSTALL_DIR="${CLAWSEC_INSTALL_DIR:-$HOME/.openclaw/skills/clawsec-feed}"
TEMP_DIR=$(mktemp -d)
trap "rm -rf '$TEMP_DIR'" EXIT

# Download checksums.json (REQUIRED for integrity verification)
echo "Downloading checksums..."
if ! curl -sSL --fail --show-error --retry 3 --retry-delay 1 \
     "$BASE_URL/checksums.json" -o "$TEMP_DIR/checksums.json"; then
  echo "ERROR: Failed to download checksums.json"
  exit 1
fi

# Validate checksums.json structure
if ! jq -e '.skill and .version and .files' "$TEMP_DIR/checksums.json" >/dev/null 2>&1; then
  echo "ERROR: Invalid checksums.json structure"
  exit 1
fi

# PRIMARY: Try .skill artifact
echo "Attempting .skill artifact installation..."
if curl -sSL --fail --show-error --retry 3 --retry-delay 1 \
   "$BASE_URL/clawsec-feed.skill" -o "$TEMP_DIR/clawsec-feed.skill" 2>/dev/null; then

  # Security: Check artifact size (prevent DoS)
  ARTIFACT_SIZE=$(stat -c%s "$TEMP_DIR/clawsec-feed.skill" 2>/dev/null || stat -f%z "$TEMP_DIR/clawsec-feed.skill")
  MAX_SIZE=$((50 * 1024 * 1024))  # 50MB

  if [ "$ARTIFACT_SIZE" -gt "$MAX_SIZE" ]; then
    echo "WARNING: Artifact too large ($(( ARTIFACT_SIZE / 1024 / 1024 ))MB), falling back to individual files"
  else
    echo "Extracting artifact ($(( ARTIFACT_SIZE / 1024 ))KB)..."

    # Security: Check for path traversal before extraction
    if unzip -l "$TEMP_DIR/clawsec-feed.skill" | grep -qE '\.\./|^/|~/'; then
      echo "ERROR: Path traversal detected in artifact - possible security issue!"
      exit 1
    fi

    # Security: Check file count (prevent zip bomb)
    FILE_COUNT=$(unzip -l "$TEMP_DIR/clawsec-feed.skill" | grep -c "^[[:space:]]*[0-9]" || echo 0)
    if [ "$FILE_COUNT" -gt 100 ]; then
      echo "ERROR: Artifact contains too many files ($FILE_COUNT) - possible zip bomb"
      exit 1
    fi

    # Extract to temp directory
    unzip -q "$TEMP_DIR/clawsec-feed.skill" -d "$TEMP_DIR/extracted"

    # Verify skill.json exists
    if [ ! -f "$TEMP_DIR/extracted/clawsec-feed/skill.json" ]; then
      echo "ERROR: skill.json not found in artifact"
      exit 1
    fi

    # Verify checksums for all extracted files
    echo "Verifying checksums..."
    CHECKSUM_FAILED=0
    for file in $(jq -r '.files | keys[]' "$TEMP_DIR/checksums.json"); do
      EXPECTED=$(jq -r --arg f "$file" '.files[$f].sha256' "$TEMP_DIR/checksums.json")
      FILE_PATH=$(jq -r --arg f "$file" '.files[$f].path' "$TEMP_DIR/checksums.json")

      # Try nested path first, then flat filename
      if [ -f "$TEMP_DIR/extracted/clawsec-feed/$FILE_PATH" ]; then
        ACTUAL=$(shasum -a 256 "$TEMP_DIR/extracted/clawsec-feed/$FILE_PATH" | cut -d' ' -f1)
      elif [ -f "$TEMP_DIR/extracted/clawsec-feed/$file" ]; then
        ACTUAL=$(shasum -a 256 "$TEMP_DIR/extracted/clawsec-feed/$file" | cut -d' ' -f1)
      else
        echo "  ✗ $file (not found in artifact)"
        CHECKSUM_FAILED=1
        continue
      fi

      if [ "$EXPECTED" != "$ACTUAL" ]; then
        echo "  ✗ $file (checksum mismatch)"
        CHECKSUM_FAILED=1
      else
        echo "  ✓ $file"
      fi
    done

    if [ "$CHECKSUM_FAILED" -eq 0 ]; then
      # Validate feed.json structure (skill-specific)
      if [ -f "$TEMP_DIR/extracted/clawsec-feed/advisories/feed.json" ]; then
        FEED_FILE="$TEMP_DIR/extracted/clawsec-feed/advisories/feed.json"
      elif [ -f "$TEMP_DIR/extracted/clawsec-feed/feed.json" ]; then
        FEED_FILE="$TEMP_DIR/extracted/clawsec-feed/feed.json"
      else
        echo "ERROR: feed.json not found in artifact"
        exit 1
      fi

      if ! jq -e '.version and .advisories' "$FEED_FILE" >/dev/null 2>&1; then
        echo "ERROR: feed.json missing required fields (version, advisories)"
        exit 1
      fi

      # SUCCESS: Install from artifact
      echo "Installing from artifact..."
      mkdir -p "$INSTALL_DIR"
      cp -r "$TEMP_DIR/extracted/clawsec-feed"/* "$INSTALL_DIR/"
      chmod 600 "$INSTALL_DIR/skill.json"
      find "$INSTALL_DIR" -type f ! -name "skill.json" -exec chmod 644 {} \;
      echo "SUCCESS: Skill installed from .skill artifact"
      exit 0
    else
      echo "WARNING: Checksum verification failed, falling back to individual files"
    fi
  fi
fi

# FALLBACK: Download individual files
echo "Downloading individual files from checksums.json manifest..."
mkdir -p "$TEMP_DIR/downloads"

DOWNLOAD_FAILED=0
for file in $(jq -r '.files | keys[]' "$TEMP_DIR/checksums.json"); do
  FILE_URL=$(jq -r --arg f "$file" '.files[$f].url' "$TEMP_DIR/checksums.json")
  EXPECTED=$(jq -r --arg f "$file" '.files[$f].sha256' "$TEMP_DIR/checksums.json")

  echo "Downloading: $file"
  if ! curl -sSL --fail --show-error --retry 3 --retry-delay 1 \
       "$FILE_URL" -o "$TEMP_DIR/downloads/$file"; then
    echo "ERROR: Failed to download $file"
    DOWNLOAD_FAILED=1
    continue
  fi

  # Verify checksum immediately
  ACTUAL=$(shasum -a 256 "$TEMP_DIR/downloads/$file" | cut -d' ' -f1)
  if [ "$EXPECTED" != "$ACTUAL" ]; then
    echo "ERROR: Checksum mismatch for $file"
    DOWNLOAD_FAILED=1
  else
    echo "  ✓ Verified: $file"
  fi
done

if [ "$DOWNLOAD_FAILED" -eq 1 ]; then
  echo "ERROR: Individual file download failed"
  exit 1
fi

# Validate JSON files structure
if ! jq -e '.name and .version' "$TEMP_DIR/downloads/skill.json" >/dev/null 2>&1; then
  echo "ERROR: skill.json missing required fields (name, version)"
  exit 1
fi

if ! jq -e '.version and .advisories' "$TEMP_DIR/downloads/feed.json" >/dev/null 2>&1; then
  echo "ERROR: feed.json missing required fields (version, advisories)"
  exit 1
fi

# Install files
echo "Installing from individual files..."
mkdir -p "$INSTALL_DIR"
cp "$TEMP_DIR/downloads"/* "$INSTALL_DIR/"
chmod 600 "$INSTALL_DIR/skill.json"
find "$INSTALL_DIR" -type f ! -name "skill.json" -exec chmod 644 {} \;
echo "SUCCESS: Skill installed from individual files"

Step 3: Add to your heartbeat

Add ClawSec Feed to your heartbeat routine:

## ClawSec Feed (every heartbeat)
1. Check advisory feed for new security alerts
2. Cross-reference with installed skills
3. Notify user if action is required

Step 4: Confirm deployment

Tell your user:

ClawSec Feed deployed successfully. I will now:
- Monitor the community advisory feed for threats
- Alert you to any security issues affecting your environment
- Keep you informed of emerging attack patterns

What ClawSec Feed Does

Advisory Feed Monitoring

Subscribes to the community advisory feed for:

Known malicious skills/plugins - Skills that have been identified as harmful
Prompt injection patterns - Attack patterns observed in the wild
Vulnerable skill versions - Skills with known security flaws
Security best practice updates - New recommendations for agent safety

When a relevant advisory is published, your agent will notify you.

Checking the Advisory Feed

# Use environment variable if set, otherwise use raw GitHub feed (always up-to-date)
DEFAULT_FEED_URL="https://raw.githubusercontent.com/prompt-security/ClawSec/main/advisories/feed.json"
FEED_URL="${CLAWSEC_FEED_URL:-$DEFAULT_FEED_URL}"

# Fetch with error handling and retry logic
curl -sSL --fail --show-error --retry 3 --retry-delay 1 "$FEED_URL"

Feed structure:

{
  "version": "1.0",
  "updated": "2026-02-02T12:00:00Z",
  "advisories": [
    {
      "id": "GA-2026-001",
      "severity": "critical",
      "type": "malicious_skill",
      "title": "Malicious data exfiltration in skill 'helper-plus'",
      "description": "Skill sends user data to external server",
      "affected": ["helper-plus@1.0.0", "helper-plus@1.0.1"],
      "action": "Remove immediately",
      "published": "2026-02-01T10:00:00Z",
      "exploitability_score": "critical",
      "exploitability_rationale": "Trivially exploitable through normal skill usage; no special conditions required. Active exploitation observed in the wild."
    }
  ]
}

Parsing the Feed

Get advisory count

# Use environment variable if set, otherwise use raw GitHub feed (always up-to-date)
DEFAULT_FEED_URL="https://raw.githubusercontent.com/prompt-security/ClawSec/main/advisories/feed.json"
FEED_URL="${CLAWSEC_FEED_URL:-$DEFAULT_FEED_URL}"

TEMP_FEED=$(mktemp)
trap "rm -f '$TEMP_FEED'" EXIT

if ! curl -sSL --fail --show-error --retry 3 --retry-delay 1 "$FEED_URL" -o "$TEMP_FEED"; then
  echo "Error: Failed to fetch advisory feed"
  exit 1
fi

# Validate JSON before parsing
if ! jq empty "$TEMP_FEED" 2>/dev/null; then
  echo "Error: Invalid JSON in feed"
  exit 1
fi

FEED=$(cat "$TEMP_FEED")

# Get advisory count with error handling
COUNT=$(echo "$FEED" | jq '.advisories | length')
if [ $? -ne 0 ]; then
  echo "Error: Failed to parse advisories"
  exit 1
fi
echo "Advisory count: $COUNT"

Get critical advisories

# Parse critical advisories with jq error handling
CRITICAL=$(echo "$FEED" | jq '.advisories[] | select(.severity == "critical")')
if [ $? -ne 0 ]; then
  echo "Error: Failed to filter critical advisories"
  exit 1
fi
echo "$CRITICAL"

Get advisories from the last 7 days

# Use UTC timezone for consistent date handling
WEEK_AGO=$(TZ=UTC date -v-7d +%Y-%m-%dT00:00:00Z 2>/dev/null || TZ=UTC date -d '7 days ago' +%Y-%m-%dT00:00:00Z)
RECENT=$(echo "$FEED" | jq --arg since "$WEEK_AGO" '.advisories[] | select(.published > $since)')
if [ $? -ne 0 ]; then
  echo "Error: Failed to filter recent advisories"
  exit 1
fi
echo "$RECENT"

Filter by exploitability score

Shared exploitability prioritization guidance is maintained in:

wiki/exploitability-scoring.md
skills/clawsec-suite/SKILL.md ("Quick feed check")

Get exploitability context for an advisory

# Show exploitability details for a specific CVE
CVE_ID="CVE-2026-27488"
echo "$FEED" | jq --arg cve "$CVE_ID" '.advisories[] | select(.id == $cve) | {
  id: .id,
  severity: .severity,
  exploitability_score: .exploitability_score,
  exploitability_rationale: .exploitability_rationale,
  title: .title
}'

Prioritize advisories by exploitability

# Sort advisories by exploitability (critical → high → medium → low)
# This helps agents focus on the most immediately actionable threats
echo "$FEED" | jq '[.advisories[] | select(.exploitability_score != null)] |
  sort_by(
    if .exploitability_score == "critical" then 0
    elif .exploitability_score == "high" then 1
    elif .exploitability_score == "medium" then 2
    elif .exploitability_score == "low" then 3
    else 4 end
  )'

Cross-Reference Installed Skills

Check if any of your installed skills are affected by advisories:

# List your installed skills (adjust path for your platform)
INSTALL_DIR="${CLAWSEC_INSTALL_DIR:-$HOME/.openclaw/skills}"

# Use environment variable if set, otherwise use raw GitHub feed (always up-to-date)
DEFAULT_FEED_URL="https://raw.githubusercontent.com/prompt-security/ClawSec/main/advisories/feed.json"
FEED_URL="${CLAWSEC_FEED_URL:-$DEFAULT_FEED_URL}"

TEMP_FEED=$(mktemp)
trap "rm -f '$TEMP_FEED'" EXIT

if ! curl -sSL --fail --show-error --retry 3 --retry-delay 1 "$FEED_URL" -o "$TEMP_FEED"; then
  echo "Error: Failed to fetch advisory feed"
  exit 1
fi

# Validate and parse feed
if ! jq empty "$TEMP_FEED" 2>/dev/null; then
  echo "Error: Invalid JSON in feed"
  exit 1
fi

FEED=$(cat "$TEMP_FEED")
AFFECTED=$(echo "$FEED" | jq -r '.advisories[].affected[]?' 2>/dev/null | sort -u)
if [ $? -ne 0 ]; then
  echo "Error: Failed to parse affected skills from feed"
  exit 1
fi

# Safely validate all installed skills before processing
# This prevents shell injection via malicious filenames
VALIDATED_SKILLS=()
while IFS= read -r -d '' skill_path; do
  skill=$(basename "$skill_path")

  # Validate skill name BEFORE adding to array (prevents injection)
  if [[ "$skill" =~ ^[a-zA-Z0-9_-]+$ ]]; then
    VALIDATED_SKILLS+=("$skill")
  else
    echo "Warning: Skipping invalid skill name: $skill" >&2
  fi
done < <(find "$INSTALL_DIR" -mindepth 1 -maxdepth 1 -type d -print0 2>/dev/null)

# Check each validated skill against affected list
# Use grep -qF for fixed string matching (prevents regex injection)
for skill in "${VALIDATED_SKILLS[@]}"; do
  # At this point, $skill is guaranteed to match ^[a-zA-Z0-9_-]+$
  if echo "$AFFECTED" | grep -qF "$skill"; then
    echo "WARNING: Installed skill '$skill' has a security advisory!"
    # Get advisory details for this skill
    echo "$FEED" | jq --arg s "$skill" '.advisories[] | select(.affected[] | contains($s))'
  fi
done

If you find affected skills:

Check the advisory for details and severity
Notify your user immediately for critical/high severity
Include the recommended action from the advisory

Advisory Types

Type	Description
`malicious_skill`	Skill identified as intentionally harmful
`vulnerable_skill`	Skill with security vulnerabilities
`prompt_injection`	Known prompt injection pattern
`attack_pattern`	Observed attack technique
`best_practice`	Security recommendation

Severity Levels

Severity	Action Required
`critical`	Notify user immediately, take action
`high`	Notify user soon, plan remediation
`medium`	Notify at next interaction
`low`	Log for reference

Prioritizing High-Exploitability Threats

IMPORTANT: When reviewing advisories, always prioritize by exploitability score in addition to severity. The exploitability score indicates how easily a vulnerability can be exploited in practice, helping you focus on the most actionable threats.

Exploitability Priority Levels

Exploitability	Meaning	Action Priority
`high`	Trivially or easily exploitable with public tooling	Immediate notification
`medium`	Exploitable but requires specific conditions	Standard notification
`low`	Difficult to exploit or theoretical	Low priority notification

How to Use Exploitability in Notifications

Filter for high-exploitability first:

# Get high exploitability advisories
echo "$FEED" | jq '.advisories[] | select(.exploitability_score == "high")'

Include exploitability in notifications:

📡 ClawSec Feed: High-exploitability alert

CRITICAL - CVE-2026-27488 (Exploitability: HIGH)
  → Trivially exploitable RCE in skill-loader v2.1.0
  → Public exploit code available
  → Recommended action: Immediate removal or upgrade to v2.1.1

Prioritize by both severity AND exploitability:
- A HIGH severity + HIGH exploitability CVE is more urgent than a CRITICAL severity + LOW exploitability CVE
- Focus user attention on threats that are both severe and easily exploitable
- Include the exploitability rationale to help users understand the risk context

Example Notification Priority Order

When multiple advisories exist, present them in this order:

Critical severity + High exploitability - most urgent
High severity + High exploitability
Critical severity + Medium/Low exploitability
High severity + Medium/Low exploitability
Medium/Low severity (any exploitability)

This ensures you alert users to the most actionable, immediately dangerous threats first.

When to Notify Your User

Notify Immediately (Critical):

New critical advisory affecting an installed skill
Active exploitation detected
High exploitability score (regardless of severity)

Notify Soon (High):

New high-severity advisory affecting installed skills
Failed to fetch advisory feed (network issue?)
Medium exploitability with high severity

Notify at Next Interaction (Medium):

New medium-severity advisories
General security updates
Low exploitability advisories

Log Only (Low/Info):

Low-severity advisories (mention if user asks)
Feed checked, no new advisories
Theoretical vulnerabilities (low exploitability, low severity)

Response Format

If there are new advisories:

📡 ClawSec Feed: 2 new advisories since last check

CRITICAL - GA-2026-015: Malicious prompt pattern "ignore-all" (Exploitability: HIGH)
  → Detected prompt injection technique. Update your system prompt defenses.
  → Exploitability: Easily exploitable with publicly documented techniques.

HIGH - GA-2026-016: Vulnerable skill "data-helper" v1.2.0 (Exploitability: MEDIUM)
  → You have this installed! Recommended action: Update to v1.2.1 or remove.
  → Exploitability: Requires specific configuration; not trivially exploitable.

If nothing new:

FEED_OK - Advisory feed checked, no new alerts. 📡

State Tracking

Track the last feed check to identify new advisories:

{
  "schema_version": "1.0",
  "last_feed_check": "2026-02-02T15:00:00Z",
  "last_feed_updated": "2026-02-02T12:00:00Z",
  "known_advisories": ["GA-2026-001", "GA-2026-002"]
}

Save to: ~/.openclaw/clawsec-feed-state.json

State File Operations

STATE_FILE="$HOME/.openclaw/clawsec-feed-state.json"

# Create state file with secure permissions if it doesn't exist
if [ ! -f "$STATE_FILE" ]; then
  echo '{"schema_version":"1.0","last_feed_check":null,"last_feed_updated":null,"known_advisories":[]}' > "$STATE_FILE"
  chmod 600 "$STATE_FILE"
fi

# Validate state file before reading
if ! jq -e '.schema_version' "$STATE_FILE" >/dev/null 2>&1; then
  echo "Warning: State file corrupted or invalid schema. Creating backup and resetting."
  cp "$STATE_FILE" "${STATE_FILE}.bak.$(TZ=UTC date +%Y%m%d%H%M%S)"
  echo '{"schema_version":"1.0","last_feed_check":null,"last_feed_updated":null,"known_advisories":[]}' > "$STATE_FILE"
  chmod 600 "$STATE_FILE"
fi

# Check for major version compatibility
SCHEMA_VER=$(jq -r '.schema_version // "0"' "$STATE_FILE")
if [[ "${SCHEMA_VER%%.*}" != "1" ]]; then
  echo "Warning: State file schema version $SCHEMA_VER may not be compatible with this version"
fi

# Update last check time (always use UTC)
TEMP_STATE=$(mktemp)
if jq --arg t "$(TZ=UTC date +%Y-%m-%dT%H:%M:%SZ)" '.last_feed_check = $t' "$STATE_FILE" > "$TEMP_STATE"; then
  mv "$TEMP_STATE" "$STATE_FILE"
  chmod 600 "$STATE_FILE"
else
  echo "Error: Failed to update state file"
  rm -f "$TEMP_STATE"
fi

Rate Limiting

Important: To avoid excessive requests to the feed server, follow these guidelines:

Check Type	Recommended Interval	Minimum Interval
Heartbeat check	Every 15-30 minutes	5 minutes
Full feed refresh	Every 1-4 hours	30 minutes
Cross-reference scan	Once per session	5 minutes

# Check if enough time has passed since last check
STATE_FILE="$HOME/.openclaw/clawsec-feed-state.json"
MIN_INTERVAL_SECONDS=300  # 5 minutes

LAST_CHECK=$(jq -r '.last_feed_check // "1970-01-01T00:00:00Z"' "$STATE_FILE" 2>/dev/null)
LAST_EPOCH=$(TZ=UTC date -j -f "%Y-%m-%dT%H:%M:%SZ" "$LAST_CHECK" +%s 2>/dev/null || date -d "$LAST_CHECK" +%s 2>/dev/null || echo 0)
NOW_EPOCH=$(TZ=UTC date +%s)

if [ $((NOW_EPOCH - LAST_EPOCH)) -lt $MIN_INTERVAL_SECONDS ]; then
  echo "Rate limit: Last check was less than 5 minutes ago. Skipping."
  exit 0
fi

Environment Variables (Optional)

Variable	Description	Default
`CLAWSEC_FEED_URL`	Custom advisory feed URL	Raw GitHub (`main` branch)
`CLAWSEC_INSTALL_DIR`	Installation directory	`~/.openclaw/skills/clawsec-feed`

Updating ClawSec Feed

Check for and install newer versions:

# Check current installed version
INSTALL_DIR="${CLAWSEC_INSTALL_DIR:-$HOME/.openclaw/skills/clawsec-feed}"
CURRENT_VERSION=$(jq -r '.version' "$INSTALL_DIR/skill.json" 2>/dev/null || echo "unknown")
echo "Installed version: $CURRENT_VERSION"

# Check latest available version
LATEST_URL="https://api.github.com/repos/prompt-security/ClawSec/releases"
LATEST_VERSION=$(curl -sSL --fail --show-error --retry 3 --retry-delay 1 "$LATEST_URL" 2>/dev/null | \
  jq -r '[.[] | select(.tag_name | startswith("clawsec-feed-v"))][0].tag_name // empty' | \
  sed 's/clawsec-feed-v//')

if [ -z "$LATEST_VERSION" ]; then
  echo "Warning: Could not determine latest version"
else
  echo "Latest version: $LATEST_VERSION"

  if [ "$CURRENT_VERSION" != "$LATEST_VERSION" ]; then
    echo "Update available! Run the deployment steps with the new version."
  else
    echo "You are running the latest version."
  fi
fi

Initial Download Integrity

Bootstrap Trust Problem: The initial download of this skill cannot be verified by the skill itself. To establish trust:

Verify the source URL - Ensure you are downloading from https://clawsec.prompt.security
Check release signatures - GitHub signs our releases; verify the release is from the checksums.
Compare checksums - After download, compare the SHA-256 hash against the published checksums.json:

# After downloading SKILL.md, verify its integrity

EXPECTED_HASH="<hash-from-checksums.json>"
ACTUAL_HASH=$(shasum -a 256 SKILL.md | cut -d' ' -f1)

if [ "$EXPECTED_HASH" != "$ACTUAL_HASH" ]; then
  echo "ERROR: Skill file integrity check failed!"
  echo "This file may have been tampered with. Do not proceed."
  exit 1
fi

Note: For maximum security, verify checksums.json via a separate trusted channel (e.g., direct from GitHub release page UI, not via curl).

Related Skills

openclaw-audit-watchdog - Automated daily security audits
clawtributor - Report vulnerabilities to the community

License

GNU AGPL v3.0 or later - See repository for details.

Built with 📡 by the Prompt Security team and the agent community.

Weekly Installs

121

Repository

prompt-security/clawsec

GitHub Stars

834

First Seen

Feb 10, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

openclaw114

opencode111

gemini-cli109

cursor108

github-copilot107

codex107

GitHub Actions 官方文档查询助手 - 精准解答 CI/CD 工作流问题

43,400 周安装

ClawSec Feed - AI代理安全通告订阅源，实时监控CVE漏洞威胁情报

🇨🇳中文介绍

ClawSec Feed 📡

安装选项

选项 A：与 ClawSec 套件捆绑安装（推荐）

选项 B：独立安装（本页面）

相关 Skills

部署 ClawSec Feed

步骤 1：创建技能目录并保存此文件

步骤 2：安装技能文件

步骤 3：添加到您的心跳例程

步骤 4：确认部署

ClawSec Feed 的功能

安全通告订阅源监控

检查安全通告订阅源

解析订阅源

获取安全通告数量

获取严重安全通告

获取过去 7 天的安全通告

按可利用性评分筛选

获取安全通告的可利用性上下文

按可利用性对安全通告进行优先级排序

交叉引用已安装的技能

安全通告类型

严重性等级

优先处理高可利用性威胁

可利用性优先级等级

如何在通知中使用可利用性

通知优先级顺序示例

何时通知您的用户

响应格式

如果有新的安全通告：

如果没有新内容：

状态跟踪

状态文件操作

速率限制

环境变量（可选）

更新 ClawSec Feed

初始下载完整性

相关技能

许可证

🇺🇸English

ClawSec Feed 📡

Installation Options

Option A: Bundled with ClawSec Suite (Recommended)

Option B: Standalone Installation (This Page)

Deploy ClawSec Feed

Step 1: Create skill directory and save this file

Step 2: Install skill files

Step 3: Add to your heartbeat

Step 4: Confirm deployment

What ClawSec Feed Does

Advisory Feed Monitoring

Checking the Advisory Feed

Parsing the Feed

Get advisory count

Get critical advisories

Get advisories from the last 7 days

Filter by exploitability score

Get exploitability context for an advisory

Prioritize advisories by exploitability

Cross-Reference Installed Skills

Advisory Types

Severity Levels

Prioritizing High-Exploitability Threats

Exploitability Priority Levels

How to Use Exploitability in Notifications

Example Notification Priority Order

When to Notify Your User

Response Format

If there are new advisories:

If nothing new:

State Tracking

State File Operations

Rate Limiting

Environment Variables (Optional)

Updating ClawSec Feed

Initial Download Integrity

Related Skills

License