The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the yq, xq, and tomlq command-line utilities to perform data extraction and modification tasks. This includes in-place file editing using the -i flag, which is standard functionality for this toolset.
[EXTERNAL_DOWNLOADS]: Installation instructions refer to well-known and official software distribution channels, including the official GitHub repository for the Python yq wrapper (kislyuk/yq), PyPI, Homebrew, and Docker Hub.
[PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection as it processes external, potentially untrusted data files (YAML, XML, TOML).
Ingestion points: The agent reads and processes configuration and data files from the project environment (e.g., docker-compose.yml, pyproject.toml, config.yml).
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from interpreting instructions that might be embedded within the processed data files.
Capability inventory: The skill possesses the capability to execute shell commands and modify files on the system.
Sanitization: No specific validation or sanitization steps for file content are included in the skill's instructions.

yq