npx skills add https://github.com/jorgealves/agent_skills --skill prompt-injection-scannerprompt-injection-scanner 是一款专为 AI 智能体时代设计的安全工具。它能识别智能体指令中的薄弱点,这些地方恶意用户可能通过向输入字段插入冲突指令来“劫持”智能体的行为。
capabilities 或指令时都应运行此工具。secret-leak-detector;本工具专门用于“指令层面”的安全。skill_path: "./agent-skills/data-processor/SKILL.md"
一份结构化报告,突出显示指令中易受提示劫持攻击的部分,并提供具体的缓解策略。
The prompt-injection-scanner is a security tool specifically for the AI agent era. It identifies weak points in agent instructions where a malicious user could potentially "hijack" the agent's behavior by inserting conflicting instructions into input fields.
capabilities or instructions for an agent skill.secret-leak-detector for credentials; this is specifically for "instruction-level" security.skill_path: "./agent-skills/data-processor/SKILL.md"
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
每周安装量
108
代码仓库
首次出现
2026年1月30日
安全审计
安装于
opencode105
github-copilot101
codex92
gemini-cli46
cursor46
kimi-cli39
A structured report highlighting parts of the instructions that are susceptible to prompt hijacking, along with concrete mitigation strategies.
Weekly Installs
108
Repository
First Seen
Jan 30, 2026
Security Audits
Installed on
opencode105
github-copilot101
codex92
gemini-cli46
cursor46
kimi-cli39
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
66,200 周安装