triage

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md, "Step 1: Gather context" and the "Reproduce" step) explicitly reads full issue tracker content — issue bodies, comments, reporter steps — and uses reporter-provided reproduction steps to run tests and decide actions, which are untrusted user-generated inputs that could influence tool use.