bug-report
Warn
Audited by Snyk on Jul 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). Step 2 fetches a Gorgias support ticket and “extract[s] all messages to understand the full bug context,” meaning the agent ingests outsider-authored customer messages/comments from the Gorgias ticket thread into the LLM context for Step 3.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata