deep-research
Warn
Audited by Snyk on Sep 15, 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 deep-research skill instructs agents to fetch web pages via arbitrary URLs and search results using
WebFetchandWebSearch, which can expose the agent to untrusted outsider-authored web content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata