attio

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI from the npm registry using npm install -g @membranehq/cli@latest. This is a vendor-owned package required for the skill's core functionality.
  • [COMMAND_EXECUTION]: The skill utilizes the membrane command-line tool to perform CRM operations, including managing connections, listing records, and executing API actions. These commands are the intended method for interacting with the Attio service through the Membrane middleware.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Attio (such as records, notes, and tasks). While this represents an attack surface where malicious content could be embedded in CRM data, the skill uses structured actions and prompts that follow typical CRM integration patterns.
  • [CREDENTIALS_SAFE]: The skill explicitly instructs agents not to ask for API keys or tokens, relying instead on Membrane's connection management system which handles authentication (OAuth/API keys) server-side, reducing the risk of local credential exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 09:46 AM