ClawHub
Back to skill

Security audit

Idea Darwin

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only idea organization skill that reads a user idea file and writes local planning files, with a broad auto-trigger caveat but no hidden or high-impact behavior found.

Install this if you want an agent to maintain an idea-evolution workspace. Use it in a dedicated project folder because it will create and update local files, and invoke it explicitly if you do not want broad brainstorming requests to automatically use this workflow.

SkillSpector

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
96% confidence
Finding
The manifest description says the skill should trigger not only for specific phrases like "/idea-darwin" but also for broad phrases such as "run a round" and for any task involving structuring, scoring, ranking, or systematic iteration of ideas. These conditions are ambiguous and overlap with common brainstorming requests, increasing the risk of unintended invocation outside a clearly bounded context.

Static analysis

No suspicious patterns detected.