The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions designed to guide an AI agent through a code review workflow. It does not perform any automated actions, file system modifications, or network requests.
[NO_CODE]: There are no scripts, binaries, or command execution patterns found in the skill files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process code provided by a user for review. While this constitutes an ingestion point for untrusted data, the skill itself lacks any capabilities (such as shell execution or network access) that would make it vulnerable to exploitation through indirect prompt injection.

code-review