ops-triage

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries GitHub using gh and "reads the full issue: body, all comments" from the repository (see SKILL.md "Show What Needs Attention" and "Step 1: Gather context"), meaning it ingests user-generated, public issue/comment content that the agent interprets to make triage decisions and take actions.