diffity-resolve

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests user-generated review comments from the diffity review session (via "diffity agent list --status open --json" / .diffity/current-session) and reads the full comment bodies and then performs code edits and resolves threads, so untrusted third‑party comment text can directly influence actions.