triage

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and interprets issue tracker content (full issue bodies, comments, reporter steps, and prior triage notes) during "Gather context" in SKILL.md — these are untrusted, user-generated inputs from the issue tracker that directly drive triage decisions and actions (labels, comments, agent briefs), so they could carry indirect prompt injections.