ClawHub
Back to skill

Security audit

Claw MBTI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple MBTI-style self-assessment for an agent, with disclosed local scoring logic and no hidden persistence or privileged access.

This appears safe to install for its stated purpose. Users should know that opening the generated result link may share the encoded personality-score parameters with the external result website.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Context Window Stuffing

Medium
Category
Memory Poisoning
Content
```javascript
// === MBTI Scoring Code ===
// Replace the answers array with your responses (-3 to 3 for Q00-Q59)
const answers = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0];

// Question metadata: [dimension, directionSign, weight]
// directionSign: -1 for first-pole (E/N/T/J/A), +1 for second-pole (I/S/F/P/Turb)
Confidence
80% confidence
Finding
Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Static analysis

No suspicious patterns detected.