nix-review
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted local .nix files, which creates an indirect prompt injection surface where code comments or strings could attempt to influence the agent's output.
- Ingestion points: Files discovered via find and read operations in SKILL.md.
- Boundary markers: Absent; there are no specific instructions to the agent to treat code content as untrusted data or ignore embedded instructions.
- Capability inventory: The agent can read/write files and execute Nix CLI tools like nix build and nix flake check.
- Sanitization: None; external code content is interpolated directly into the context for analysis without escaping or validation.
Audit Metadata