github

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly fetches and inspects user-generated GitHub content (e.g., "gh pr checks", "gh run view ", and "gh api repos/.../pulls/...") — including PRs, issues, and CI logs — which are untrusted third-party inputs the agent would read and that could materially influence management actions.