amocrm

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from AmoCRM, including lead notes, contact information, and company records. Because this data can be influenced by external parties (e.g., customers filling out forms), it presents a surface for indirect prompt injection if the agent interprets the data as instructions.
  • Ingestion points: Data retrieved from AmoCRM via membrane action run and membrane request commands.
  • Boundary markers: None specified in the instructions for separating untrusted data from the system prompt.
  • Capability inventory: Executes shell commands via the Membrane CLI and performs network operations through the Membrane proxy.
  • Sanitization: No explicit sanitization or filtering of CRM data is described.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the Membrane CLI (@membranehq/cli) from the official npm package registry to facilitate authentication and API interactions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 07:19 AM