k8s-yaml-validator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and interprets public third-party content — Stage 3 instructs CRD documentation lookups via mcp__context7__query-docs and a web.search_query fallback, and Stage 4 configures kubeconform to pull CRD schemas from raw.githubusercontent.com — so untrusted web content is read and used to drive validation decisions.

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

• Potentially malicious external URL detected (high risk: 0.70). The detect_crd_wrapper.sh script will create a venv and run "pip install pyyaml" at runtime, causing the skill to fetch and install/execute code from PyPI (e.g. https://pypi.org/project/PyYAML/), which is a required runtime dependency for CRD detection.