arcads-external-api

Pass

Audited by Gen Agent Trust Hub on May 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (ffmpeg, ffprobe) and CLI tools (whisper) to analyze video frames and transcribe audio. These operations are performed locally and are necessary for the primary functions of analyzing and cloning video styles.
  • [EXTERNAL_DOWNLOADS]: Instructions are provided for the user to install well-known and trusted third-party tools such as ffmpeg and the openai-whisper Python package. These dependencies are standard for the intended media processing tasks.
  • [DATA_EXFILTRATION]: Network activity is restricted to the legitimate vendor domain external-api.arcads.ai. The skill documentation focuses on interacting with this specific service to manage marketing creative assets.
  • [CREDENTIALS_UNSAFE]: The skill handles authentication using an API key stored in environment variables. It explicitly instructs the user to store the key in a .env file and provides warnings against exposing the key in chat history or shared files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 23, 2026, 02:45 PM
Security Audit — agent-trust-hub — arcads-external-api