helm-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill's Stage 2 "Lookup CRD Documentation" explicitly directs the agent to query external sources (Context7 via mcp__context7__query-docs, operator official docs, and general web search) and to use those public third‑party documents to determine CRD fields and chart generation, so untrusted web content would be read and could influence subsequent tooling and actions.