ClawHub
Back to skill

Security audit

Feynman Think Method

Security checks for vulnerabilities and agentic risk

Overview

This is a static learning-method skill with disclosed boundaries and no code, credentials, persistence, or hidden execution behavior.

Installers should treat this as a study and reasoning aid, not as a source of verified financial, legal, medical, or current-market facts. Avoid providing raw personal, client, health, financial, or confidential business data unless it is minimized and desensitized.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Confidence
89% confidence
Finding
The metadata states '中文为主，英文关键术语保留', which imposes a default language behavior in natural language. Under the policy rule, language constraints should either be user-selectable or clearly justified; this line does not present it as an opt-in choice.

Static analysis

No suspicious patterns detected.