list-building

Warn

Audited by Snyk on Aug 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests untrusted, outsider-authored free text when it uses the beginner workflow’s “GET COMPANY SUMMARY” step, which prompts the LLM to “visit this website /company_domain” and summarize content scraped from a user-selected external website/domain.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill repeatedly instructs running the command "COLDIQ_API_KEY= npx -y @coldiq/mcp@latest" (e.g., SKILL.md and multiple sub-skills), which at runtime fetches and executes remote npm code (the ColdIQ MCP) and is relied on by the skill's primary "ColdIQ-first" workflow.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 17, 2026, 06:01 AM
Issues
2
Security Audit — snyk — list-building