nixpkgs-development

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with external data sources such as Nix source files and GitHub Pull Requests, which presents a surface for indirect prompt injection attacks.
  • Ingestion points: External Nix expressions and GitHub PR content processed via tools like gh and nix-build as described in SKILL.md and references/contributing.md.
  • Boundary markers: The agent is instructed to use specific bundled reference files and pinned source snapshots, reducing the risk of following instructions from untrusted external documentation.
  • Capability inventory: Uses nix-build, gh search, and nixpkgs-review, which are capable of code evaluation and repository interaction.
  • Sanitization: Explicitly requires user authorization for sensitive tool flags (e.g., merge or approve) that act on the user's identity.
  • [SAFE]: The skill acts as a development guide for the Nixpkgs project. It reinforces security best practices, such as the use of build sandboxing and secure secret handling, and contains no evidence of malicious intent or hidden code.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 03:53 PM