dogfood

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow reads outsider-authored free text from GitHub issues/PRs at runtime (e.g., gh pr view ... and gh issue view ... bodies for tunan:project and prior tunan:dogfood issues), which can then be incorporated into the agent’s LLM context when generating the analysis/report.