qa

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches PR metadata and diffs from GitHub (gh pr view, gh pr diff) and ingests commit logs/changed files (including contributions from forks or external users) as part of its required workflow to drive QA planning and issue/file creation, exposing it to untrusted, user-generated third-party content that could influence agent actions.