github

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

• Third-party content exposure detected (high risk: 0.90). The skill uses gh commands that fetch and display public GitHub content (e.g., gh pr list, gh pr view --comments, gh issue view, gh run view --log-failed, gh gist view, and gh api repos/...), which ingests untrusted, user-generated data from public repos/issues/PRs that the agent is expected to read and interpret.