NYC
skills/vm0-ai/vm0-skills/bitrix/Gen Agent Trust Hub

bitrix

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • PROMPT_INJECTION (LOW): Potential for indirect prompt injection via data ingested from the Bitrix24 API.\n
  • Ingestion points: API responses from Bitrix24 methods (e.g., user.get.json, crm.lead.list.json) which are processed by the agent.\n
  • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions within the retrieved data.\n
  • Capability inventory: Shell execution via bash -c, network requests via curl, and file system write access in /tmp.\n
  • Sanitization: Absent; data returned from the API is read directly by the agent without explicit validation or escaping.\n- COMMAND_EXECUTION (LOW): The skill utilizes bash -c to execute curl commands. While this is used to handle environment variable interpolation, it creates a surface for shell injection if the agent interpolates user-controlled parameters (such as lead IDs or filter values) without proper escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:55 PM