The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses poetry to execute common development tools (pre-commit, ruff, mypy, pytest) in a shell environment. These commands are restricted to the local development environment and are essential for the skill's purpose of code validation.- [INDIRECT_PROMPT_INJECTION]: The skill processes the contents of the local repository for validation purposes, which constitutes an attack surface for indirect prompt injection if the files being analyzed contain malicious instructions.
Ingestion points: The skill reads files from the project repository, specifically within paths like http_py/ for type-checking.
Boundary markers: None specified; the agent is instructed to read tool output directly.
Capability inventory: Shell command execution via poetry run for linting and test execution.
Sanitization: The skill does not implement specific sanitization or filtering of the code content it validates.

validate-code