github-issues

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

• Third-party content exposure detected (high risk: 0.90). The skill's required validation and triage workflow explicitly instructs the agent to read and act on GitHub issues and comments via the gh CLI (e.g., "gh issue view [number] --comments" in the Validation Workflow), which are untrusted, user-generated third‑party contents that can materially influence subsequent tool use and decisions.