blog-outline
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's workflow (Step 2: "Use WebSearch" and "Use WebFetch on the top 2-3 results") instructs the agent to fetch and analyze top search results and page content from public websites, which are untrusted third-party sources and are used to drive the outline and content-gap decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata