skills/lev-os/agents/lev/Gen Agent Trust Hub

lev

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Documents installation of the @lev-os/lev package via NPM, which is a vendor-owned resource matching the author 'lev-os'.
  • [COMMAND_EXECUTION]: Provides documentation for various CLI commands including system management, daemon control, and troubleshooting steps such as sudo chown for local configuration directories.
  • [PROMPT_INJECTION]: The skill processes natural language triggers to route requests, presenting a potential surface for indirect prompt injection. Ingestion points: user-provided query strings for research or analysis. Boundary markers: none specified in the skill instructions. Capability inventory: execution of local CLI commands and creation of project artifacts. Sanitization: none specified.
  • [SAFE]: Performs local network health checks on daemon services using curl against localhost endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:02 AM