pull-request-management

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime GitHub PR operations (e.g., gh pr view ... --comments, gh pr view ... --json comments/reviews, gh pr diff ...) ingest outsider-authored free text from PR conversation content—such as review comments and issue/PR discussion bodies written by other users—into the agent’s LLM context via the GitHub API/CLI response.