0codekit

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the membrane CLI to run actions, manage connections, and perform proxy requests to external APIs.
  • [EXTERNAL_DOWNLOADS]: Directs users to install the @membranehq/cli package via NPM to enable functionality.
  • [PROMPT_INJECTION]: The skill is designed to process data from a wide array of external services including databases, emails, and chat messages, which creates a significant surface for indirect prompt injection. Ingestion points: Data retrieved from 0codekit actions and proxy requests documented in SKILL.md. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation. Capability inventory: Subprocess execution via the Membrane CLI. Sanitization: The documentation does not specify any sanitization or validation steps for content retrieved from external integrations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:56 AM