neon-one

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to install and interact with the Membrane CLI, including global package installation (npm install -g), authentication flows (membrane login), and action execution (membrane action run).
  • [EXTERNAL_DOWNLOADS]: The skill downloads the @membranehq/cli package from the public npm registry. This is a verified resource from the skill author ('membranedev').
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by interpolating user-supplied natural language into shell commands for action discovery and creation.
  • Ingestion points: Natural language input used in --intent and action create arguments in SKILL.md.
  • Boundary markers: Absent in shell command templates.
  • Capability inventory: Ability to run subprocesses via the CLI and execute actions against the Neon One API.
  • Sanitization: Not specified in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 06:50 PM
Security Audit — agent-trust-hub — neon-one