telnyx-voice-streaming-python

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by processing real-time voice transcriptions. If the resulting text is fed into an LLM without appropriate safeguards, an attacker could potentially influence the agent's behavior via spoken instructions.
  • Ingestion points: The transcription webhook event described in SKILL.md provides external, untrusted text data to the system.
  • Boundary markers: Absent; there are no instructions or delimiters defined to help the agent distinguish between its own logic and the transcribed data.
  • Capability inventory: The skill utilizes the telnyx SDK to perform call control actions like start_forking, start_streaming, and start_transcription.
  • Sanitization: Absent; the example implementation does not include logic for filtering or escaping the transcribed content before use.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 03:10 AM