narrator-ai-cli

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the narrator-ai-cli tool. The commands are well-defined and rely on structured data passed through CLI arguments. The skill includes specific rules requiring user confirmation before executing potentially high-cost or creative tasks.
  • [EXTERNAL_DOWNLOADS]: The skill installs its primary dependency, narrator-ai-cli, directly from the vendor's official GitHub repository (NarratorAI-Studio). This is documented as a prerequisite for functionality.
  • [CREDENTIALS_UNSAFE]: The skill utilizes the NARRATOR_APP_KEY environment variable for authentication, which is a standard and secure practice for CLI tools. There are no instances of hardcoded secrets, and the documentation correctly advises users to keep their keys private.
  • [DATA_EXFILTRATION]: Network operations are directed solely to the vendor's official API endpoint (openapi.jieshuo.cn). Data flow is restricted to the necessary parameters for video generation and file management related to the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 02:14 PM