tend-pr-tick

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly reads and interprets user-generated PR comments and CI failure output as part of workflow (see "Read State", "Comment Classification", "CI Failure Triage", and "Routing" in SKILL.md) and uses those inputs to decide fixes, amend manifests, invoke /do, push changes, and reply, so untrusted third‑party content can materially influence actions.