rhdh-operator-pr-test

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

• Third-party content exposure detected (medium risk: 0.30). /rhdh-forge reads GitHub PR comments and diff content for a specified redhat-developer/rhdh-operator PR, and those outsider-authored comment bodies are then parsed at runtime to extract container image URLs.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill directly pulls and deploys container images from quay.io at runtime (e.g., docker://quay.io/rhdh-community/operator:TAG and quay.io/rhdh-community/operator-catalog:), which fetches and executes remote code on the cluster.