github-multi-repo

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and parses content from public GitHub sources (e.g., gh repo list, gh api repos/:owner/:repo/contents/package.json, gh search repos, and cloning repos to read CLAUDE.md/package.json), so it ingests untrusted, user-generated repository content that the agent is expected to read and could enable indirect prompt injection.