ClawHub
Back to skill

Security audit

Minimalist Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese-language business decision review prompt with no code, file access, network use, credentials, or persistence.

Install this if you want a Chinese-language minimalist business-decision reviewer. Be aware it may activate on broad Chinese phrases like asking for evaluation or checking something, so users may prefer narrower triggers or explicit language-selection guidance.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is written entirely in Chinese and directs a fixed Chinese-language interaction without indicating that it is locale-specific or allowing adaptation to the user's language. This can create unsafe or misleading behavior if invoked for users in other languages, because instructions may be misunderstood, misapplied, or surfaced without informed user choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords include very common phrases such as '我该怎么做', '帮我评估', and '检查一下', which are broad enough to match many unrelated user requests. This can cause unintended skill invocation, overriding more appropriate behaviors or injecting this business-review framing into conversations where it does not belong.

Content

No source excerpt is available for this finding.