ClawHub
Back to skill

Security audit

China Claw

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a market-research helper, but it includes an unrelated China ICP filing workflow that could route users into regulatory guidance outside the advertised purpose.

Review this skill before installing if you only want OpenClaw-alternative market research. The ICP filing section should be removed or split into a separate, clearly scoped compliance skill that requires current official-source verification.

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
  • 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 (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill is scoped to researching China-based OpenClaw alternatives, but it also embeds an unrelated ICP filing/备案 workflow. This scope drift can cause incorrect skill invocation and make the agent answer regulatory/domain-administration questions under a product-research skill, increasing the chance of misleading guidance and bypassing safer domain-specific routing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Mixing China-specific filing guidance into a market-research skill without documented locale or jurisdiction constraints is unsafe because it may prompt the agent to provide quasi-regulatory instructions outside the skill's advertised purpose. In practice, this can lead to overbroad matching for unrelated user requests and delivery of incomplete or context-insensitive compliance guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.