ClawHub
Back to skill

Security audit

Prd Prototype Review

Security checks across malware telemetry and agentic risk

Overview

This skill is a document-review assistant that reads user-selected PRD/prototype files and can apply documented edits after confirmation.

Install this if you want an assistant to review and improve PRD/prototype documents. Before confirming any patch application, make sure the agent is working only on the intended files and review the proposed edits, since the skill can modify product documents after approval.

SkillSpector

By NVIDIA
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
Confidence
92% confidence
Finding
The skill description includes multiple broad trigger phrases such as '评审PRD/原型', 'review需求文档', and '评审报告', which can cause the skill to activate for loosely related requests. Overly broad activation increases the chance of unintended invocation on unrelated or sensitive documents, leading to unnecessary file reads or modifications in contexts the user did not explicitly intend.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.