Idea Darwin 中文版

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed idea-iteration skill that reads and writes local project idea files for its stated purpose, with no executable code, network access, or credential use.

Install this if you want an agent-managed local idea workflow. Use it in a dedicated project folder, review generated cards and reports before relying on them, and be aware that broad idea-ranking or idea-iteration requests may cause the skill to read and update local idea project files.

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

High
Confidence
94% confidence
Finding
The skill explicitly instructs automatic triggering for any task involving structured ideas, scoring, ranking, or iterative brainstorming, which is broader than a narrowly scoped command trigger. This can cause inappropriate activation on ordinary brainstorming or note-organization tasks, leading the agent to override user intent, apply unnecessary file operations, and expose unrelated workspace content to the skill’s workflow.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal