skills/tensorslab/skills/tl-video/Gen Agent Trust Hub

tl-video

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is well-structured and follows secure development practices for its intended purpose of AI video generation.
  • [COMMAND_EXECUTION]: The skill uses Python scripts to interact with the TensorsLab API and handle the OAuth-like authorization process. These scripts are invoked with user-provided prompts and parameters according to the defined workflow.
  • [DATA_EXFILTRATION]: Communication is restricted to 'api.tensorslab.com' and 'tensorai.tensorslab.com'. These are official vendor domains used for task submission, status polling, and user authentication. No unauthorized external data transmission was detected.
  • [CREDENTIALS_UNSAFE]: API keys are managed using a dedicated configuration file in the user's home directory ('~/.tensorslab/.env'). The authorization script facilitates this via a local HTTP server on the loopback interface ('127.0.0.1'), which is a standard and safe practice for local application authentication.
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated video files from URLs provided by the authenticated TensorsLab API and saves them to a local directory ('./tensorslab_output/').
  • [SAFE]: The code utilizes 'yaml.safe_load' when reading configuration and mapping files, preventing potential unsafe deserialization vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 01:54 AM