ai-voice-bots

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several external services and frameworks including Pipecat, LiveKit, Twilio, Deepgram, and ElevenLabs. All referenced sources are well-known industry providers or official documentation repositories.
  • [INDIRECT_PROMPT_INJECTION]: The skill architecture involves processing untrusted user input (speech-to-text transcripts). The provided patterns address data privacy and quality (e.g., PCI redaction, profanity filtering), representing the standard attack surface for conversational agents.
  • [COMMAND_EXECUTION]: The provided Python scripts (voice_latency_audit.py and call_quality_scorer.py) are benign utility tools designed for performance analysis and quality scoring.
  • [OBFUSCATION]: No obfuscated code, hidden URLs, or suspicious character encoding techniques were detected in any of the skill's files or metadata.
  • [SAFE]: The skill demonstrates high-quality technical documentation and follows security best practices, such as using placeholders for credentials and implementing data compliance patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 02:03 PM