telnyx-ai-assistants-java
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for interacting with AI assistants which creates an attack surface for indirect prompt injection. Ingestion points: assistant chat content and tool outputs. Boundary markers: none identified in examples. Capability inventory: Telnyx API resource management. Sanitization: none demonstrated.
- [SAFE]: The skill correctly uses environment variables for secret management via TelnyxOkHttpClient.fromEnv() and identifies as an official SDK integration from a recognized vendor.
Audit Metadata