build-support-agent
Warn
Audited by Snyk on Aug 12, 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). Customer chat messages are ingested via a support-platform webhook (customer message plus message history) and fed into the classifier/RAG tools at runtime (steps 1–5 and processTicket), so outsider-authored free text can be submitted into the monitored queue/feed the workflow consumes.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata