developer-atlas
Warn
Audited by Snyk on Sep 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The agent skill uses Tavily search and extract tools to fetch web pages, documentation, and repository discussions based on user queries, placing it in active search/fetch of external outsider-authored content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata