gentle-ai-branch-pr

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly requires fetching and checking GitHub issues via "gh issue view --repo Gentleman-Programming/gentle-ai", which ingests user-generated, public issue content that the workflow uses to decide whether to proceed (e.g., require status:approved), so untrusted third-party content can influence actions.