helm-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs the agent to run "helm show values " and "helm show readme " (including oci://registry/chart) to ingest chart defaults and README content from public chart registries, and that untrusted, user-provided content directly influences generated values and subsequent Helm install/upgrade actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs fetching chart defaults at runtime (e.g., via "helm show values oci://registry/chart"), so remote OCI registry URLs (oci://registry/chart) would be fetched and their content would directly control the generated Helm values and prompts.