telnyx-voice-advanced-python

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the "telnyx" Python package. This is the official SDK for the service provided by the author and is considered a safe vendor resource.
  • [PROMPT_INJECTION]:
  • Ingestion points: Untrusted data enters the system through webhook payloads, as seen in the "handle_webhook" example in "SKILL.md".
  • Boundary markers: Explicit boundary markers or warnings for the agent to ignore instructions within the webhook data are absent.
  • Capability inventory: The skill can perform call control actions such as sending DTMF tones, starting/stopping SIPREC sessions, and updating call state via the "client.calls.actions" methods.
  • Sanitization: While the skill correctly demonstrates cryptographic signature verification using "client.webhooks.unwrap()" to ensure authenticity, it lacks explicit sanitization of specific payload fields (like "client_state") before they might be used in further processing or prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 10:57 AM