Security audit
Security checks for vulnerabilities and agentic risk
This is a local skill-auditing helper whose file-reading behavior is disclosed and aligned with its security-review purpose.
Install this only if you want a local skill-review assistant. Give it explicit skill-directory paths, avoid pointing it at broad private folders, and treat its verdicts as heuristic because the permission boundaries and some advanced review claims are not tightly specified.
The skill text describes capabilities that imply file reading, network access, and shell-oriented analysis steps, but it does not declare corresponding permissions. This creates a trust and review gap: operators may approve or run the skill without understanding the actual access it expects, increasing the chance of over-privileged execution or unsafe deployment.
The activation phrases include broad everyday expressions such as '审一下' and '查一下这个skill', which can cause accidental invocation outside a clearly intended security-review context. Over-broad triggering is dangerous for a skill with analysis capabilities because it may activate unexpectedly, inspect unintended content, or interfere with normal conversations and workflows.
Detected: suspicious.exposed_secret_literal, suspicious.prompt_injection_instructions
