truefoundry-integrations

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a set of instructions and templates for managing LLM provider integrations on the TrueFoundry platform using the vendor's official APIs and CLI tools.
  • [SAFE]: Security-centric instructions are prominent, explicitly forbidding the handling of raw API keys and mandating the use of tfy-secret:// references for all sensitive credentials.
  • [SAFE]: The included shell scripts (tfy-api.sh, tfy-version.sh) are transparent and perform legitimate tasks such as making authenticated REST calls to the vendor's platform and checking the local version of the truefoundry SDK.
  • [SAFE]: External dependencies and container image references (e.g., from AWS ECR and GHCR) are consistent with the vendor's infrastructure and established technology partners like HuggingFace.
  • [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized privilege escalation was found across any of the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:04 AM