check-vanta

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests vulnerability data from external third-party APIs (e.g., Vanta via "<api_base>/vulnerabilities", Snyk API, Dependabot/GitHub API) and parses descriptions/CVE identifiers which are then used to decide fixes, create issues, and drive commits/PRs, so untrusted external content can materially influence agent actions.