The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to manage the CLI lifecycle, including checking versions, performing interactive logins, and running Python scripts to inspect local configuration.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-provided tenant URLs into shell commands.
Ingestion points: User input for the tenant URL in Step 4 of SKILL.md.
Boundary markers: The URL is wrapped in double quotes in the tfy login command, but no explicit delimiters or "ignore embedded instructions" warnings are provided to the agent.
Capability inventory: The skill has access to standard Bash tools and Python as defined in the allowed-tools metadata.
Sanitization: There is no evidence of validation, sanitization, or escaping of the user-provided URL string before execution.
[EXTERNAL_DOWNLOADS]: The skill installs the truefoundry Python package via pip or uv. As this is a vendor-owned package, this is considered an expected functional behavior for an onboarding tool.
[COMMAND_EXECUTION]: The skill reads the ~/.truefoundry/credentials.json file using a Python script. While this involves accessing sensitive credential metadata on the local file system, it is restricted to the vendor's own application directory for state verification purposes.

truefoundry-onboard