gh-code-search

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

• Third-party content exposure detected (high risk: 0.90). This skill issues GitHub searches and retrieves file contents (e.g., via "gh search code" and "gh api repos/owner/repo/contents/..."), which causes the agent to ingest and interpret untrusted, user-generated content from public GitHub repositories.

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

• Potentially malicious external URL detected (high risk: 1.00). This skill runs gh api at runtime to fetch repository file contents (e.g. gh api "repos/owner/repo/contents/path/to/file" -> https://api.github.com/repos/owner/repo/contents/path/to/file), and those fetched files are used as code/context driving the agent's responses, so the external content directly controls prompts.