Back to skill

Security audit

Bitrix24 Cli

Security checks for vulnerabilities and agentic risk

Overview

The scanners flag a missing confirmation for destructive CRM actions and search that reaches messages and notes beyond the stated purpose, so the verdict is suspicious with medium confidence.

Before installing, consider whether you are comfortable with searches that include messages and notes, and with MCP writes that may run without asking you to confirm each operation. The scanner covered all six listed components, but analysis was marked partial because two local references could not be resolved, so the evidence is incomplete.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
references/mcp.md
Finding

MCP executes confirmation-gated destructive operations without confirmation

Content
View full analysis

Impact

A caller can delete real CRM records without the expected per-operation confirmation. Other ask-gated writes can also trigger portal automation that messages or bills clients.

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

Most commands directly support the declared CRM purpose. However, the all-source search explicitly includes messages and notes, expanding access beyond the declared CRM data and locally synchronized deals and leads. The mismatch is limited to that broader search scope.

Content

No source excerpt is available for this finding.