ai-tool-handoff
Warn
Audited by Snyk on Jul 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests the tool’s extraction results and then reads/compares actual clauses from the VDR documents (outsider-authored contract text from third parties), which becomes LLM-readable prose in the agent’s context during QA and judgment.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata