proof-orchestrator
Warn
Audited by Snyk on Oct 26, 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 required workflow for the optional DeepSeek audit invokes an MCP chat tool (
mcp__llm_chat__chat) to ingest external AI-generated review text from DeepSeek, which constitutes indirect prompt injection risk from a monitored third-party service response.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata