ClawHub
Back to skill

Security audit

prd-impact-analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documented PRD impact-analysis helper that reads product requirements and code context to produce reviewable change specs, with no bundled executable code or hidden persistence.

Install only if you are comfortable giving the agent access to the relevant PRD and codebase for analysis. Review generated specs before allowing any optional code-generation or workflow step to modify source code, especially for permission, database, or API changes.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Hidden Instructions

High
Category
Prompt Injection
Content
变更伪代码:
   ```vue
   <!-- Before -->
   <el-select v-model="filterRole">
     <el-option label="管理员" value="admin" />
     <el-option label="用户" value="user" />
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The skill metadata and description are written to enforce Chinese-language behavior without presenting any user-language negotiation or fallback, which can mislead downstream agents into responding in a fixed language regardless of user preference. This is not a direct code-execution issue, but it is a real prompt-safety and usability weakness because it can override operator expectations and reduce transparency in multilingual environments.

Static analysis

No suspicious patterns detected.