ClawHub
Back to skill

Security audit

KOL

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language guidance skill for KOL collaboration management and does not include code, tool use, credential handling, persistence, or hidden behavior.

Before installing, understand that this skill will activate for KOL collaboration management tasks and provide general SOP guidance. It does not appear to run commands or access data, but users should still apply their own legal, platform, and privacy review when using it for real campaigns.

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
93% confidence
Finding

The description is broad enough that the skill may activate for general KOL-related work, increasing the chance it is invoked outside its intended scope. Over-broad activation can cause prompt/skill hijacking at the routing layer, where a loosely matched skill injects instructions or content into unrelated workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.