agent-reach

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

• Third-party content exposure detected (medium risk: 0.30). The workflow explicitly instructs the agent to read GitHub issues and pull requests (gh issue list, gh issue view) which are authored by third parties.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of an arbitrary, personal GitHub repository via pip install https://github.com/Panniantong/agent-reach/archive/main.zip, which is an unverified runtime external dependency with weak/unknown provenance, warranting a high risk tier.