ghwf7-pr

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md's "Load Context" step explicitly instructs the agent to fetch and read Issue/PR bodies, comments, and reviews via gh issue view / gh pr view, which are user-generated GitHub content that could contain arbitrary instructions affecting whether the agent marks the PR Ready for Review.