tools-ui

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). SKILL.md's "With Agent Component" example explicitly registers a 'search_web' tool described as "Search the web", which indicates the agent will ingest open-web/public search results (untrusted third-party content) as part of its workflow and those results can influence subsequent tool calls/decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 01:44 AM