nixos
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform administrative tasks on a NixOS system, specifically creating and removing a lock file at
/etc/nixos/.nixos-build. It also authorizes building and switching system configurations, which are high-privilege operations necessary for the skill's primary purpose. - [PROMPT_INJECTION]: As the skill is designed to resolve externally described issues, it possesses an attack surface for indirect prompt injection.
- Ingestion points: User-provided or system-generated descriptions of NixOS issues (SKILL.md).
- Boundary markers: The instructions do not define delimiters or specific safety instructions to ignore potential commands embedded within the problem descriptions, although it does explicitly prohibit decrypting secrets.
- Capability inventory: Capability to modify system files in
/etc/nixos/and execute system-wide configuration changes via NixOS tools. - Sanitization: No explicit sanitization or validation of the input 'issues' is mentioned.
Audit Metadata