understand-pr

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow fetches outsider-authored PR content (PR title/body, diff, and linked issue bodies/comments) via gh pr view, gh pr diff, and gh issue view, which are then read into the agent’s LLM context for analysis—an indirect prompt-injection path from third-party text.