web-research
Warn
Audited by Snyk on Feb 15, 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). This skill explicitly directs the agent to use "available web search tools" to gather information from the open web and to "cite specific sources with URLs," meaning the agent will fetch and read untrusted public third-party content (public websites/URLs) that could carry indirect prompt injection.
Audit Metadata