systematic-debugging

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

• Third-party content exposure detected (high risk: 0.80). The skill's Phase 0 workflow explicitly instructs using GitHub commands (e.g., gh issue view / gh issue edit) to read and act on GitHub issues, which are untrusted, user-generated third-party content that the agent is expected to interpret and use to decide whether to proceed—creating a clear avenue for indirect prompt injection.