setup-transcriptformer-remote-tool

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads a Python wheel file (tuplatform_connect-0.3.0-py3-none-any.whl) from connect.aiscientist.tools. The download includes a SHA-256 integrity hash (sha256=3fad5eee5ecf7887a693d93ccd1aa112dc0955617a885d1fc3daded0030f9ae0) to ensure the file has not been tampered with. While this is an external domain, the documentation presents it as a specific tool (tuplatform-connect) required for the skill's primary purpose of connecting to the ToolUniverse platform.
  • [COMMAND_EXECUTION]: The instructions involve executing several shell commands and Python scripts (e.g., tu remote login, tu serve, and validation scripts). These are standard operational procedures for setting up and testing a remote tool implementation. The skill explicitly warns against putting sensitive tokens like TOOLUNIVERSE_API_TOKEN in shell arguments, which is a positive security practice.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill mentions managing credentials through TOOLUNIVERSE_SERVICE_KEY and .env files. It includes a specific warning to keep provider data, weights, caches, and credentials outside of Git and to bind services to loopback (127.0.0.1) to prevent unintended network exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 08:20 AM
Security Audit — agent-trust-hub — setup-transcriptformer-remote-tool