The Agent Skills Directory

[SAFE]: The skill is designed to manage security and content moderation policies. It includes multiple security warnings in its documentation regarding the use of external endpoints and the verification of third-party resources.
[COMMAND_EXECUTION]: The skill utilizes a local helper script scripts/tfy-api.sh to perform authenticated curl requests to the platform's REST API. This script includes protections against path traversal and validates HTTP methods.
[EXTERNAL_DOWNLOADS]: The skill recommends installing the official vendor package truefoundry from PyPI and references container images from well-known and trusted registries such as AWS ECR, HuggingFace, and NVIDIA NGC.
[CREDENTIALS_UNSAFE]: The skill manages the TFY_API_KEY for authentication. It follows standard practices by reading this from environment variables or a .env file and provides clear guidance on using the platform's secret management system (tfy-secret://) to avoid exposing raw credentials in configuration files.

truefoundry-guardrails