gtm-plays-11

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt instructs users to set an API key inline in a shell command (COLDIQ_API_KEY= npx ...), which encourages embedding a secret directly in command text and could force an agent or user to paste the secret verbatim into generated commands — an insecure pattern that risks exfiltration.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running the command "COLDIQ_API_KEY= npx -y @coldiq/mcp@latest" (SKILL.md:15), which will fetch and execute remote npm package code at runtime to connect the ColdIQ MCP, so it is a runtime external dependency that executes remote code.