architect-create-llm-test
Warn
Audited by Snyk on Sep 27, 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 reads past customer conversations via
GET /v1/convai/conversations/{conversation_id}, which contain outsider-authored free text from end-users interacting with the agent.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata