gentle-ai-branch-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to run "gh issue view --repo Gentleman-Programming/gentle-ai" and rely on the issue's status:approved, which means it fetches and interprets user-generated GitHub issue content (an open/public third-party source) as part of its required workflow.