ClawHub
Back to skill

Security audit

Six Thinking Hats

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed decision-analysis helper that stores local preferences, with no executable code or evidence of hidden or destructive behavior.

Install only if you are comfortable with the agent keeping local notes about your decision-analysis preferences and, if enabled, recent analyses. Review or delete ~/six-thinking-hats/ if you do not want that history retained.

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 (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
- Mixing hats → analysis becomes confused, key perspectives missed
- Skipping Red → ignoring intuition that might catch what logic misses
- Black without Yellow → decisions feel negative, good options get rejected
- Green without constraints → impractical ideas waste time
- No Blue at end → analysis without actionable conclusion

## Related Skills
Confidence
80% confidence
Finding
Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The instruction to 'save immediately' user preferences creates persistent storage of user data without any notice, consent, or clear data-minimization boundary. Even if the stored data is only preferences, it can accumulate behavioral profiling information over time, which is risky in a decision-support skill that is explicitly told to analyze the user's style and day-to-day behavior.

Static analysis

No suspicious patterns detected.