writing-designs
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Step 2 "Research" requires performing web searches and visiting/verifying at least five external URLs (engineering blogs, technical articles, and GitHub) via WebFetch, so the agent fetches and ingests untrusted public third-party content that it will read and interpret.
Audit Metadata