IdeaForge

Security checks across malware telemetry and agentic risk

Overview

This skill is a planning assistant that turns rough product ideas into structured project plans, with no hidden code, persistence, or privileged actions found.

Before installing, be aware that the skill may activate for broad idea-making phrases and will likely encourage more structured planning than a casual chat. It may also ask the agent to look up reference links for technical planning. It does not request privileged access or run code.

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
95% confidence
Finding
The trigger phrases include very common conversational patterns such as '帮我做个工具', '想做一个东西', and '有个idea', which can match ordinary user requests outside the intended scope. This creates a real risk of unintended activation, causing the skill to intercept unrelated conversations and steer behavior unexpectedly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal