PRD 文档生成器

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 6:34 AM UTC
• Version:
  1.0.0

Overview

This is a documentation-only PRD generator with no executable code, network behavior, persistence, or hidden privilege requests.

Installers should know this skill may activate for broad PRD or requirements-document requests. It appears safe from a security perspective, but users who want tighter routing may prefer more explicit invocation such as asking to generate a PRD or product requirements document.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger list is overly broad and includes generic phrases such as '写需求' and '需求文档' that can easily appear in normal conversation outside the intended PRD-generation use case. This can cause unintended skill activation, leading the agent to override user intent, inject irrelevant structured output, or route sensitive requests into the wrong workflow.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill’s trigger phrases are broad enough to match many generic writing or product-planning requests, which can cause the skill to activate outside its intended scope. Over-broad activation is dangerous because it may steer users into a rigid PRD-generation workflow when they wanted other assistance, increasing the chance of irrelevant guidance, prompt-surface expansion, or unintended disclosure of project details during unnecessary clarification steps.

VirusTotal

64/64 vendors flagged this skill as clean.