guardrails
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides tools and instructions for managing security guardrails on the TrueFoundry platform. It includes several security-conscious design choices, such as mandatory user confirmation for workspace selection and warnings against hardcoding credentials in manifests.- [COMMAND_EXECUTION]: The skill uses a helper script (
scripts/tfy-api.sh) to perform authenticated API requests viacurlto the platform's backend. The script includes basic security checks, such as validating the HTTP method and preventing path traversal in the API path. This is standard and expected behavior for interacting with the service.- [EXTERNAL_DOWNLOADS]: The documentation suggests installing thetruefoundryPython package (truefoundry==0.5.0), which is the official SDK for the platform provider. It also references an official GitHub repository for a custom guardrails template (truefoundry/custom-guardrails-template). These are legitimate vendor resources.- [DATA_EXFILTRATION]: No unauthorized data exfiltration patterns were found. Network operations are directed towards the user's configured TrueFoundry instance (TFY_BASE_URL) for legitimate resource management tasks.
Audit Metadata