The Agent Skills Directory

[SAFE]: No security issues were detected in this skill. The skill is entirely instructional and serves to guide the AI agent's reasoning process during code reviews.
[NO_CODE]: The skill does not include any executable scripts, binary files, or external dependencies. It relies solely on natural language instructions for the LLM.
[PROMPT_INJECTION]: The instructions contain task-specific constraints (e.g., "Do not flatten or remove structure", "Do not manufacture simplification") which are benign and intended to refine the output quality rather than bypass safety filters or override agent behavior.
[DATA_EXFILTRATION]: There are no patterns suggesting data exfiltration. The skill does not use network-capable tools or access sensitive filesystem paths.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute remote code. It does not reference any external packages or repositories.

lean-review