🔍 BigPlan · 产品调研(市场分析·技术评估·供应链·产品规格方案)| Product Research & Planning

Security checks across malware telemetry and agentic risk

Overview

This is a plain product-research prompt skill with no executable code or hidden system access, though some trigger phrases are broad.

Reasonable to install for product research and planning. Treat BOM, pricing, market-size, and timeline outputs as estimates that need verification before business decisions, and be aware the broad trigger phrases may invoke the skill when you only meant a general analysis request.

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
93% confidence
Finding
The trigger phrases include very broad, generic requests such as '帮我分析' and '想做一款', which can match many unrelated user intents and cause the skill to activate unexpectedly. In a skill that drives market/product research workflows, this can override more appropriate handling, produce irrelevant outputs, and increase the risk of unintended data gathering or misleading guidance.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal