truefoundry-workspaces

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions and automated bash logic in references/prerequisites.md to install the vendor's official package truefoundry (version 0.5.0) and its dependency pydantic via standard package managers. This is standard configuration for platform-specific tools.
  • [COMMAND_EXECUTION]: The skill utilizes two helper scripts, scripts/tfy-api.sh and scripts/tfy-version.sh, to perform environment compatibility checks and execute authorized API calls via curl. The tfy-api.sh script includes security measures to prevent path traversal and ensures that API keys are only handled through secure environment variables or local environment files.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection as it ingests and processes data from the TrueFoundry API to configure deployments.
  • Ingestion points: Data retrieved from cluster and workspace listing endpoints via scripts/tfy-api.sh.
  • Boundary markers: Instructions mandate the use of formatted tables and explicit user confirmation for all workspace selections and deployment targets.
  • Capability inventory: Network operations (curl), shell execution (tfy CLI), and file system writes (manifest generation).
  • Sanitization: Path traversal protection in the API helper script and explicit warnings in references/container-versions.md forbidding the agent from fetching content from external release pages.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 03:58 PM