deep-research
Warn
Audited by Snyk on Aug 10, 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). In Step 2/3/4 the skill requires sub-agents to perform WebSearch and WebFetch, then read and summarize whatever free text appears on the searched/fetched web pages (which can include outsider-authored injection content) before writing it into the report.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata