bridgebound-firmographic-15

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt shows an inline API-key usage pattern ("COLDIQ_API_KEY= npx ...") that instructs placing a secret verbatim on the command line, which requires the LLM/user to embed the exact key and is an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow relies on ColdIQ MCP/API fetching firmographic/company intelligence from an external service at runtime (e.g., via mcp__coldiq__search_companies / mcp__coldiq__find_people), which can include outsider-authored free text/content in the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "COLDIQ_API_KEY= npx -y @coldiq/mcp@latest" (SKILL.md:13), which fetches and executes remote npm package code at runtime, so an external dependency is used to run remote code.