iso27001-gap

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow for the skill operates on “user-provided context” and “analyz[es] documents, code, or configurations,” meaning outsider-authored free text can be ingested via the runtime inputs that the agent analyzes (with only instruction-following guidance being injection-hardened rather than removing the ingestion).