attio

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI (@membranehq/cli) from the npm registry. This is a standard installation of a tool provided by the vendor (membranehq/membranedev) to facilitate the integration.
  • [COMMAND_EXECUTION]: The skill's primary functionality is delivered through the execution of membrane CLI commands in the local environment. These commands are used for authentication, connection management, and interacting with the Attio API through Membrane's managed infrastructure.
  • [PROMPT_INJECTION]: The skill exhibits surface area for indirect prompt injection as it retrieves data from Attio (such as records, notes, and task descriptions) which could contain malicious instructions. However, the skill explicitly instructs the agent to use structured output (--json) and rely on the platform's action schemas, which mitigates the risk of the agent misinterpreting data as commands.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 02:00 PM
Security Audit — agent-trust-hub — attio