The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the depot CLI tool for managing infrastructure, workflows, and secrets. All commands are standard for the tool's stated purpose and interact with the vendor's own services (depot.dev).
[PROMPT_INJECTION]: The skill interacts with external, potentially untrusted data sources, creating a surface for indirect prompt injection.
Ingestion points: Existing GitHub Action workflow files (parsed during depot ci migrate) and CI run logs (retrieved via depot ci logs).
Capability inventory: The skill utilizes the depot CLI to manage secrets, run code in remote environments, and modify local files in the .depot/ directory.
Boundary markers: No explicit delimiters are used to wrap content from logs or migrated workflows to distinguish it from system instructions.
Sanitization: There is no evidence of sanitization or filtering of workflow content or log output before the agent processes or displays them.

depot-ci