Kommo Automation

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill setup requires connecting to a hosted MCP endpoint at https://rube.app/mcp, which is the author's infrastructure for managing the CRM integration.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from an external CRM system, which presents an attack surface where malicious instructions embedded in CRM records could attempt to influence agent behavior.
  • Ingestion points: Data retrieved from Kommo leads, tasks, and custom fields via tools like KOMMO_LIST_LEADS as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the CRM data.
  • Capability inventory: The skill provides full CRUD (Create, Read, Update, Delete) capabilities for leads and tasks, allowing the agent to modify the CRM state based on processed data.
  • Sanitization: No specific sanitization, filtering, or validation logic is prescribed for the content retrieved from the CRM.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 04:44 AM