deep-research
Warn
Audited by Snyk on Aug 9, 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 provided skill content (“Deep Research Guide”) defines a general plan to search and gather from external sources, implying the agent may ingest outsider-authored free text from those sources (via runtime browsing/search/fetch in the gather phase).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata