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 handleWebhook example within SKILL.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, and hangup as detailed in SKILL.md.
  • Sanitization: The skill utilizes the official Telnyx SDK's client.webhooks().unwrap() method to perform Ed25519 signature verification on incoming requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 10:35 AM