whats-next

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

• Third-party content exposure detected (high risk: 0.70). High likelihood: the runtime workflow explicitly reads multiple within-thread files (e.g., seed.md, decisions.md, proposal.md, etc.) and uses their contents to generate the chat reply, and those files are outsider-authored whenever the operating user did not author them (e.g., threads/issues/PR-like artifacts authored by others).