twilio-conversation-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from various external channels, such as SMS, Voice, WhatsApp, and Chat. This content is retrieved and processed by the agent, creating a surface for indirect prompt injection if the messages contain malicious instructions.
- Ingestion points: Untrusted message content is retrieved via the
GET /Conversations/{id}/Communicationsendpoint documented inSKILL.md. - Boundary markers: The provided code examples do not demonstrate the use of delimiters or specific instructions to treat retrieved communication bodies as data rather than instructions.
- Capability inventory: The skill enables network operations to the Twilio API to list, read, and manage conversation lifecycle events.
- Sanitization: No explicit sanitization or content filtering of the conversation body is demonstrated in the integration patterns.
Audit Metadata