truefoundry-gateway
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill demonstrates strong security posture by enforcing the use of
tfy-secret://references for all credentials (API keys, AWS/GCP tokens), preventing sensitive data from being hardcoded in manifests. - [SAFE]: Explicit instructions are provided to avoid requesting raw API keys from the user, and to warn the user if they provide them, which helps prevent accidental credential exposure in chat logs.
- [SAFE]: The skill includes security warnings regarding the use of external guardrail providers and OpenAPI specs, advising users to verify that remote endpoints are trusted and organization-controlled.
- [SAFE]: All external URLs and technology references (e.g.,
truefoundry.com,truefoundry.ai) are associated with the vendor's official infrastructure and well-known, trusted cloud providers (AWS, Google, Azure). - [SAFE]: The execution environment is appropriately restricted via
allowed-tools, limiting the agent to necessary utilities likecurl,python, and the vendor's own API script.
Audit Metadata