handoff-notes
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). At runtime the skill uses Composio to call Gorgias APIs to list tickets and then fetch full message threads (Step 2–3), which will ingest outsider-authored customer/support messages and ticket body text into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata