update-mcp
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses curl to perform GET and PUT requests to a LiteLLM proxy API. This behavior is consistent with the skill's purpose of managing server registrations.
- [CREDENTIALS_UNSAFE]: Authentication is handled through the LITELLM_API_KEY environment variable. This is a secure method for providing credentials to the tool without hardcoding them in the instruction file.
- [SAFE]: No evidence of prompt injection, obfuscation, or remote code execution was found. The skill operates transparently within its defined administrative scope.
Audit Metadata