intercom
Warn
Audited by Snyk on Mar 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch and read user-generated Intercom content (e.g., "List Conversations", "Get Conversation", and "List/Get Article" API calls in the core APIs and workflows), so untrusted third‑party messages/articles from customers are ingested and used to drive replies/assignments, enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata