codebase-audit

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 interpret external dependency advisories (e.g., "gh api repos///dependabot/alerts" and npm audit) in references/dependency-audit.md and SKILL.md, and uses those untrusted third‑party advisories to decide fix strategies and create PRs, so external content can materially influence actions.