pr-auto-improve

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 diffs via "gh pr diff" and "mgr-gitnerd" (Analysis Pipeline and Implementation Flow in SKILL.md), which are user-submitted PR contents the agent reads and uses to generate and drive fixes, so it ingests untrusted third-party content that could carry indirect prompt-injection instructions.