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
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 28, 2026, 01:12 PM
Issues
1
Security Audit — snyk — agent-tools