The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill instructions focus on logical comparisons of code and documentation style within a local repository context.
[COMMAND_EXECUTION]: The skill uses git status --porcelain to identify modified files for auditing. This is a standard use of the git tool and does not present a security risk.
[INDIRECT_PROMPT_INJECTION]: The skill reads content from project files to identify patterns. While these files are external inputs, the risk of indirect prompt injection is minimal as the skill's output is reviewed and applied by the user one step at a time.

precedent