ClawHub
Back to skill

Security audit

Feynman Think Method

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk educational prompt skill for Feynman-style learning, with no executable code or hidden data access.

Install this if you want responses shaped around Feynman-style explanation and first-principles questioning. Be aware it may activate for broad learning prompts and may default to Chinese unless your agent or prompt asks for another language.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill's trigger examples are broad everyday prompts such as not being able to explain a concept clearly or wanting to understand bottom-layer logic. This can cause the skill to activate in many general conversations without clear boundaries, increasing the chance it overrides more appropriate domain-specific behavior or is applied where the user did not intend it.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
Mandating Chinese as the primary language without user choice can override user preference and reduce transparency in multilingual environments. While not a direct security exploit, it can impair usability, consent, and safe operation if users cannot fully understand the skill's outputs or instructions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.