ClawHub
Back to skill

Security audit

法律检索助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese legal-research instruction skill with no code, persistence, credential access, or hidden execution behavior, though users should treat its safety and legal-accuracy claims cautiously.

Install only if you want a Chinese-language legal research helper for the listed areas. Do not rely on its self-asserted CLEAN or verified labels as legal or platform assurance, and verify legal citations with authoritative current sources before acting on them.

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
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are generic legal-help terms that can match ordinary user requests, so the skill may activate in situations broader than the user expects. In a legal-assistance context, overly broad invocation can route sensitive legal queries into this skill without clear consent or scope boundaries, increasing the chance of unintended handling or misleading task selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description indicates Chinese-language operation without presenting it as a user-selectable preference or clearly documenting a locale restriction. This can cause misunderstanding, incorrect output language, or reduced usability for users expecting another language, which is a scope and UX safety issue rather than a direct exploit path.

Content

No source excerpt is available for this finding.