The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill's maintenance scripts reference the official Zig language domain (ziglang.org) to fetch and update documentation. This is a trusted service and does not pose a security risk.
[COMMAND_EXECUTION]: The detect_version.py script executes the zig version command. This is a static, local operation used to configure the skill's reference paths based on the user's environment and does not involve untrusted input.
[COMMAND_EXECUTION]: The init_skill.py and code_generator.py scripts perform local file system writes to generate project scaffolding and code templates. These operations are transparent and consistent with the skill's purpose as a development tool.
[PROMPT_INJECTION]: An indirect prompt injection surface was identified in the project analysis logic.
Ingestion points: The detect_version.py script reads user-controlled files such as build.zig, build.zig.zon, and .zig source files.
Boundary markers: No specific delimiters or safety instructions are used when the agent reads these files to find version markers.
Capability inventory: The skill has the ability to execute local commands (zig version) and write files to disk.
Sanitization: Files are processed using regular expression matching to detect language patterns rather than being directly executed or used as instruction inputs.

zig-programming