telnyx-voice-java
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external webhook events and has the capability to execute API commands based on that data.
- Ingestion points: Incoming webhook payloads are processed in the
handleWebhookexample withinSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for data extracted from the webhooks.
- Capability inventory: The skill possesses capabilities to perform sensitive telephony operations including
dial,answer,transfer,bridge, andhangupas detailed inSKILL.md. - Sanitization: The skill utilizes the official Telnyx SDK's
client.webhooks().unwrap()method to perform Ed25519 signature verification on incoming requests.
Audit Metadata