The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses git diff and git status to analyze project history. These commands are necessary for the skill's primary function and are limited to the local repository context.
[DATA_EXPOSURE]: The skill reads project source code and rules files. This access is required to identify discrepancies between documentation and implementation; no sensitive system-level files (e.g., SSH keys, environment variables) are accessed.
[PROMPT_INJECTION]: The skill processes untrusted data in the form of codebase diffs. While this presents an indirect prompt injection surface where malicious code comments could attempt to influence rule suggestions, the skill's specific focus on architectural invariants and minimal edits provides a restrictive context that limits the impact of such attempts.

rules-check-drift