hol-guard

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow uses plugin-scanner lint/verify (e.g., plugin-scanner lint . / plugin-scanner verify .) to scan local plugin/skill/package files that are authored by the provider user (outsider to the agent), creating an injection surface through free text contained in those files.