define-icp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes an example that directly embeds an API key into a shell command ("COLDIQ_API_KEY= npx -y @coldiq/mcp@latest"), which is an insecure pattern that would require placing the secret verbatim into a command or output.

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

• Third-party content exposure detected (medium risk: 0.65). High likelihood that runtime LLM context includes outsider-authored free text because the required workflow uses ColdIQ MCP/API (“search_companies”/“enrich_company”) to retrieve live company intelligence and then the agent uses that returned content to score and respond.