telnyx-ai-assistants-javascript
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines methods that ingest external data (such as user chat content and assistant instructions) into the AI context. While this represents a potential attack surface, it is the core functionality of the AI assistant SDK.\n
- Ingestion points: Assistant instructions in
client.ai.assistants.create()and message content inclient.ai.assistants.chat()(SKILL.md).\n - Boundary markers: Not explicitly defined in the SDK examples.\n
- Capability inventory: SDK methods allow for assistant management, communication via SMS, and tool integration.\n
- Sanitization: The provided examples do not illustrate explicit input sanitization, as the primary responsibility for filtering malicious content lies with the underlying LLM and Telnyx platform.
Audit Metadata