nixos

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill's installation instructions in README.md and the header of install.sh recommend a common installation pattern where a remote script from the author's GitHub repository is piped directly into bash. This allows the execution of code from the author's repository during the setup phase.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for the agent to fetch the latest documentation from the official NixOS organization on GitHub (github.com/NixOS) when local reference files are inadequate. These downloads target well-known and reputable technical resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from external documentation files, creating a potential surface for indirect prompt injection.
  • Ingestion points: Documentation files in references/*.md and remote fetching from github.com/NixOS.
  • Boundary markers: Absent. The skill maps user topics directly to documentation blocks.
  • Capability inventory: The AI agent uses its available tools to assist the user based on these documentation sources.
  • Sanitization: Absent. Documentation is processed as plain text.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 11:35 PM