nix-flake-organization
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by reading and refactoring existing repository files which may contain malicious instructions.
- Ingestion points: The agent reads the existing directory structure and Nix source files within the repository.
- Boundary markers: The instructions do not provide specific delimiters or ignore-markers to isolate project content from the agent's logic.
- Capability inventory: The skill requires capabilities to move directories, rewrite Nix files, and execute verification commands like
nix flake check. - Sanitization: The skill lacks validation or sanitization of ingested file content during the reorganization process.
- [EXTERNAL_DOWNLOADS]: The skill incorporates the blueprint library from the numtide GitHub repository as a standard Nix flake dependency.
Audit Metadata