kubernetes-operator

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime tools (notably scripts/crd_validator.py, scripts/reconcile_lint.py, and scripts/operator_capability_audit.py) read CRD/controller/operator repository files from paths provided by the caller (e.g., --crd, --controller, --operator-dir), so an outsider can supply arbitrary free-text via uploaded or otherwise tenant-controlled files that the tooling ingests without selecting specific predefined items.