docker-audit

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

• Third-party content exposure detected (high risk: 0.70). The required workflow scans Dockerfile/compose files found under the provided [path] (e.g., via find and grep), so any outsider-authored Dockerfile/compose text in that directory can be ingested into the agent’s LLM context through the generated audit report/findings.