github-actions-management

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and inspects GitHub repository data and run logs (e.g., list_runs, get_run, get_run_logs returning logs zip URLs for owner/repo), which are untrusted, user-generated third-party content that the agent must read and use to decide actions like rerun/cancel/trigger workflows.