repo-explore

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (SKILL.md "Clone" and "Explore" sections and examples) instructs the agent to shallow-clone arbitrary public git repositories (e.g., GitHub URLs) and read/interpret their files, meaning untrusted, user-generated content from the open web is ingested and can influence the agent's analysis and actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill performs runtime git clones of arbitrary repositories (git clone --depth 1 <repo_url>, e.g. https://github.com/user/cool-sdk) and then reads that fetched code to drive its exploration/reporting, so external repo contents directly influence the agent's outputs.