conversations
Warn
Audited by Snyk on Aug 21, 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). In the “conversations” skill, the runtime workflow reads outsider-authored inbox message text by calling the provider API to list threads and fetch messages (e.g.,
GET /v1/conversationsandGET /v1/conversations/{conversationId}/messages), where the messages originate from external contacts.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata