The Agent Skills Directory

[SAFE]: The skill contains only Markdown instructions and reference materials. It does not include executable scripts, binary files, or automated network requests.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (Zig source code and diffs) which serves as an ingestion point for potential indirect prompt injection. The skill lacks explicit boundary markers or input sanitization, though the capability inventory is limited to standard developer tools like zig fmt and zig version. This is a standard risk for code-assisting skills and is mitigated by the highly structured review process defined in the skill.

zig-code-review