ClawHub
Back to skill

Security audit

HAI Agent Framework

Security checks for vulnerabilities and agentic risk

Overview

This skill describes a useful agent framework, but it also enables automatic conversation-memory persistence and event-triggered local scripts without clear user controls.

Review before installing. Use this only if you are comfortable with automatic local hooks and saved conversation memory; do not enable or add the referenced .hai scripts until you have reviewed them, limited what they can store or execute, and confirmed how to disable hooks and delete stored memory.

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)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly states that conversation records are automatically analyzed and saved to the `memory/` directory, but it does not provide a clear user-facing warning, consent mechanism, retention policy, or description of what data is persisted. In an agent framework, this can lead to unintended collection and storage of sensitive prompts, secrets, or personal information, increasing privacy and compliance risk.

Static analysis

No suspicious patterns detected.