The Agent Skills Directory

[SAFE]: The skill provides documentation for using standard Nix ecosystem utilities such as nix hash, nix-prefetch-url, and nix-prefetch-github. These tools are intended for computing hashes and fetching source code for reproducible package builds.
[INDIRECT_PROMPT_INJECTION]: The skill includes placeholders for external data such as repository URLs and hash strings. Although these are ingestion points for untrusted data, the skill does not instruct the agent to disregard safety protocols or process the data in an unsafe manner.
Ingestion points: Placeholders for <url>, <owner>, <repo>, and <hash> in SKILL.md.
Boundary markers: None.
Capability inventory: Execution of standard Nix CLI utilities via shell.
Sanitization: None.

nix-hash