ClawHub
Back to skill

Security audit

需求文档变动影响检查

Security checks for vulnerabilities and agentic risk

Overview

This is a plain instruction-only skill for checking whether related requirement documents need updates after a main document changes.

Install this if you want Chinese-language assistance comparing requirement document changes across related files. When using it, specify the main document, the change source, and the exact related documents to inspect, especially if those documents contain private business requirements.

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
Confidence
85% confidence
Finding
The trigger description includes broad natural-language examples such as generic change-impact phrasing that can overlap with ordinary user requests. This can cause the skill to activate when the user did not intend a multi-document impact analysis, potentially pulling in unnecessary documents or bypassing a more appropriate workflow.

Natural-Language Policy Violations

Medium
Confidence
74% confidence
Finding
The skill metadata and operating instructions assume Chinese-only interaction without any language negotiation or fallback. In multilingual environments this can lead to user misunderstanding, incorrect analysis output, or silent workflow errors if the user provides requirements in another language.

Static analysis

No suspicious patterns detected.