brass

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package globally via npm to interact with the Membrane platform.
  • [COMMAND_EXECUTION]: The instructions involve executing several shell commands using the membrane CLI, including authentication (login), connection management (connect), and data operations (action run, request).
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests data from an external source (Brass API).
  • Ingestion points: Data enters the agent context through the output of membrane action run and membrane request (documented in SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided documentation.
  • Capability inventory: The agent can perform subprocess calls via the membrane CLI to query or modify data on the Brass platform.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the Brass API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 01:42 AM