skill-security-auditor

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill audits local or cloned git repositories containing AI agent skills and documentation, which may include untrusted third-party code and markdown content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The script accepts a user-supplied git repository URL as a command-line argument and executes git clone to retrieve and audit it, constituting an arbitrary, user-selected operational dependency on a remote repository with weak/unknown provenance.