pipecat-friday-agent

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements best practices for secret management by using environment variables and a .env file template to handle API keys for OpenAI and Google, preventing credential exposure.
  • [SAFE]: All identified dependencies, such as pipecat-ai and python-dotenv, are legitimate, well-known packages hosted on official registries.
  • [PROMPT_INJECTION]: The skill processes untrusted voice input as its primary data source in scripts/friday_agent.py. While there are no boundary markers to separate user speech from system instructions, the agent's capabilities are confined to audio output, posing no risk to the host system or sensitive data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:13 PM
Security Audit — agent-trust-hub — pipecat-friday-agent