iac-security

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs contacting public third‑party services and registries (e.g., the kubesec HTTP API via curl to https://v2.kubesec.io/scan, conftest pull from oci://ghcr.io/policies/kubernetes, and use of external checks via checkov --external-checks-dir), so the agent could ingest untrusted third‑party policies/scan results that would influence scanning decisions and next actions.