ClawHub
Back to skill

Security audit

Unix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language engineering workflow with no executable code, persistence, credential handling, or hidden data access.

Install this if you want a structured Chinese workflow for careful engineering tasks. Be aware it may activate broadly and may make the agent ask clarification questions before coding unless you explicitly request a direct path.

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
92% confidence
Finding

The skill metadata and content strongly imply Chinese-only operation without offering language negotiation, which can cause the agent to respond in an unexpected language and reduce user comprehension. This is primarily a safety and usability issue rather than a direct security exploit, but it can still contribute to misunderstanding of scope, approvals, or risk-related instructions during agent execution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation guidance is overly broad, especially phrases like '用户输入需求' and '要求严谨分析/最小成本交付时使用', which can match many ordinary conversations and cause the skill to trigger unexpectedly. Unintended invocation can override the assistant’s normal behavior, forcing a rigid multi-stage workflow and degrading user intent alignment, which is a real control-plane risk for agent behavior even though it is not direct code execution.

Content

No source excerpt is available for this finding.