ClawHub
Back to skill

Security audit

产品工坊（Product Workshop）

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese product-management workshop skill made of templates and checklists, with no executable or hidden high-impact behavior found.

Install this if you want a Chinese-language product-management framework with structured templates. Be aware it may activate broadly on product-related requests and steer answers into its six-step workflow.

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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger description is very broad, covering most product-planning, analysis, PRD, research, prioritization, agile, and retrospective requests. In an agent environment, this can cause the skill to activate for a large share of normal conversations, unexpectedly steering outputs toward the skill’s fixed workflow and reducing user control or causing prompt-scope interference.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The usage instructions say to apply the skill whenever the user raises a product-related task and then force a stage-classification workflow. Because the boundaries are not clearly defined, the skill may over-apply itself, hijack loosely related requests, and constrain the assistant into a predefined process even when the user did not ask for that structure.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill content and activation description are written entirely in Chinese and present a fixed Chinese-language operating mode without offering a language choice. This can override the user’s preferred language, create confusing outputs, and increase the chance of accidental activation mismatch in multilingual environments.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.