ClawHub
Back to skill

Security audit

CRM

Security checks for vulnerabilities and agentic risk

Overview

This is a simple CRM guidance skill with no executable code, persistence, credential use, or hidden data access.

Installers should understand this skill is general CRM advice in Chinese. Review its recommendations before applying them to real customer data, especially around consent, unsubscribe handling, and sensitive-data permissions.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The phrase "在开展CRM管理相关工作时调用" describes invocation in very broad terms and does not define specific triggers, boundaries, or exclusion conditions. This could overlap with many routine business conversations about CRM and cause unintended skill activation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.