get-pr-comments

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md "Fetch Comments" section explicitly instructs using gh api to retrieve GitHub pull-request and issue comments (user-generated content) and the skill's required output format directs the agent to read and present those comment bodies, so untrusted third-party content from GitHub could inject instructions that influence subsequent decisions or actions.