bunnyshell

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: Uses the membrane command-line interface to interact with the Bunnyshell platform and manage local connections.
  • [EXTERNAL_DOWNLOADS]: Fetches the @membranehq/cli tool from the official NPM registry and makes network requests to Bunnyshell endpoints.
  • [PROMPT_INJECTION]: Ingests untrusted data from external API responses, creating a surface for indirect prompt injection.
  • Ingestion points: Output from membrane action run and membrane request commands (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided.
  • Capability inventory: Subprocess execution of the membrane CLI (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the received data is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 12:07 PM