The Agent Skills Directory

[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it instructs the agent to process untrusted data and then execute commands based on that content.
Ingestion points: The agent is guided to ingest user-provided Zig source code, project configurations (build.zig, build.zig.zon), and compiler error messages from the conversation context.
Boundary markers: The instructions lack defined delimiters or specific prompts to treat the ingested code as data only or to ignore instructions embedded in comments or strings within the code.
Capability inventory: The skill directs the agent to execute shell commands through the Verification Workflow section, including zig build and zig build test.
Sanitization: There is no mention of sanitizing or validating the ingested content before it is processed by the compiler or build system.
[COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands using the Zig toolchain (e.g., zig build, zig build test, zig build -Doptimize=ReleaseFast test) as part of a development and verification workflow.
[EXTERNAL_DOWNLOADS]: The skill references documentation and community repositories from official and well-known sources, including ziglang.org, github.com, codeberg.org, and zigistry.dev. These are used for standard reference and illustrating dependency management patterns.

ziglang