performing-container-security-scanning-with-trivy

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

• Third-party content exposure detected (high risk: 0.70). This skill explicitly scans container images from remote registries (SKILL.md "Scan Container Images" / prerequisites mention "Container registry credentials") and scripts/agent.py runs trivy on a user-specified image and ingests/parses the resulting scan data to drive gate decisions, meaning untrusted third-party image content can indirectly influence agent decisions.