audit-llm-security

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

• Third-party content exposure detected (low risk: 0.10). Exclusion: this skill’s runtime workflow is a read-only OWASP LLM security audit that only instructs the assessor to observe prompt/tool/probe behavior and optionally run benign in-app policy probes, not to ingest outsider-authored free text without targeting and controlled scope.