shidi
Warn
Audited by Snyk on Oct 22, 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 workflow ingests arbitrary user-uploaded PDFs and external academic literature via web search, APIs, and fetch scripts, allowing outsider-authored text and content to be parsed and processed by the agent.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata