docs-seeker

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

• Third-party content exposure detected (medium risk: 0.30). The skill workflow instructs the agent to clone and analyze arbitrary GitHub repositories using repomix, which processes untrusted external code and repository text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the installation and execution of external tools (npm install -g repomix, git clone) from arbitrary repositories without verification mechanisms, creating a weak/unknown operational runtime dependency.