ClawHub
Back to skill

Security audit

prd-writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PRD-writing helper with no evidence of hidden execution, persistence, data theft, or destructive behavior.

Install this if you want a Chinese-language workflow for drafting PRDs. Review the output sources and assumptions, especially for market sizing or competitive research, because the skill guides document creation rather than guaranteeing factual validation.

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
91% confidence
Finding

The invocation text is broad enough to match common product-planning requests such as 写PRD、产品方案、产品定义、产品立项, which can cause the skill to activate outside a narrowly intended scope. Over-broad triggering increases the chance of unintended routing, causing the agent to apply this workflow when the user wanted brainstorming, strategy discussion, or a different document type, which can mis-handle user intent and propagate low-quality or inappropriate outputs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and examples are Chinese-only and do not state whether this is a locale restriction or whether other languages are supported. This can lead to incorrect routing or poor user experience for non-Chinese requests, and in multilingual agents may cause unintended activation or exclusion based on language rather than actual task fit.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.