The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns or security risks identified. The skill's instructions are focused on standard code review practices.
[COMMAND_EXECUTION] (LOW): The skill instructs the agent to use standard tools (git, gh) to retrieve code changes. These commands are localized to the repository specified and are necessary for the skill's primary function.
[PROMPT_INJECTION] (LOW): The skill is designed to ingest and analyze external code changes (Category 8: Indirect Prompt Injection). While the code being reviewed is untrusted and could contain malicious instructions, the skill does not possess high-risk capabilities (like write access or arbitrary execution) that would lead to significant compromise. The impact is limited to the accuracy of the review itself.

code-review