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/clipackage 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
--intentandaction createarguments inSKILL.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