The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/test_skill.py script utilizes subprocess.run() to execute the package's internal validation and analysis scripts. This usage is standard for development tools to verify their own functionality and is limited to executing known scripts within the skill's directory.
[PROMPT_INJECTION]: The skill processes external source code, which represents an indirect prompt injection attack surface. Malicious code could contain comments designed to manipulate agent behavior. The skill mitigates this risk by explicitly framing all tool outputs as 'review prompts' and 'heuristics' rather than authoritative verdicts, while providing detailed manual review rubrics to guide the agent's reasoning.
[EXTERNAL_DOWNLOADS]: The skill contains references to well-known technology documentation and GitHub repositories for language-specific best practices. These references are for documentation purposes and do not involve the execution of untrusted remote code.

strong-types