The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides instructions to download and execute installation scripts for the uv tool from Astral's official domain.
Evidence in rules/pkg-uv.md: curl -LsSf https://astral.sh/uv/install.sh | sh and powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex".
These commands are standard installation procedures for well-known developer tools provided by established technology organizations.
[INDIRECT_PROMPT_INJECTION]: The skill configures several tools that process local project data, creating a potential surface for indirect prompt injection if an agent processes code containing adversarial instructions.
Ingestion points: The agent is instructed to use tools like ruff, mypy, and pyscn to analyze all Python files (**/*.py) and configuration files (pyproject.toml) within a project.
Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted code content from agent instructions during analysis.
Capability inventory: The skill utilizes subprocess execution for linting (ruff check), formatting (ruff format), type checking (mypy), testing (pytest), and package management (uv).
Sanitization: No explicit sanitization or filtering of code content is implemented before it is processed by the analysis tools.

tooling