setup-agent-skills

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and read issue bodies and comments from third-party issue trackers (e.g., GitHub via gh issue view and GitLab via glab issue view) — untrusted, user-generated content that the agent will interpret and use to make triage/QA and other actioning decisions.