trivy

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

• Third-party content exposure detected (high risk: 0.80). The skill's commands (e.g., trivy repo https://github.com/org/repo, trivy image <image:tag>, and references to public registries like public.ecr.aws/org/image) instruct scanning of arbitrary public repositories and container images, causing the agent to fetch and interpret untrusted, user-generated third‑party content.