ClawHub
Back to skill

Security audit

Prd Prototype Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PRD/prototype review workflow that reads user-specified documents, creates a report, and only applies document patches after user confirmation.

Before installing, be aware that the skill may create review reports and, after you confirm, edit PRD or prototype files. Use it when you are intentionally asking for PRD/prototype review, and review proposed patches before approving them.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill declares very broad trigger phrases such as “评审PRD/原型”, “review需求文档”, and “评审报告”, which can easily match ordinary user requests that are not intended to invoke this powerful workflow. Because the skill reads documents and can later modify PRD/prototype files, unintended invocation increases the chance of unauthorized or surprising file access and document changes within normal conversations.

Content

No source excerpt is available for this finding.