agent-tools
Warn
Audited by Snyk on Aug 28, 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 skill provides access to search tools (Tavily, Exa) and LLMs via
belt app run, which allows searching and processing arbitrary web content (low risk) and interacting with Twitter feeds (medium risk through social feed consumption).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata