academic-deep-research
Warn
Audited by Snyk on Apr 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's required Phase 3 workflow and Tool Usage Sequence explicitly mandates using web_search (count=20) and web_fetch on primary sources to ingest and analyze content from the open web/public sources (Tool Configuration and "For Each Theme — Cycle 1/2" sections), meaning untrusted third-party pages will be read and used to drive research decisions and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata