The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute project-specific commands such as test suites, build scripts, or type-checkers discovered within the repository's configuration files (e.g., Makefile, package.json).
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it is designed to ingest and act upon untrusted content from the codebase (code, plans, and documentation) which could contain instructions meant to influence the agent's behavior.
[DATA_EXFILTRATION]: The skill uses Read, Grep, and Glob tools to perform comprehensive analysis of the project's files to gather evidence for the critique process.

critique