ClawHub
Back to skill

Security audit

Self Improver Lite

Security checks for vulnerabilities and agentic risk

Overview

This skill is transparent and purpose-aligned, but it allows automatic service restarts and persistent configuration changes without clearly bounded user confirmation.

Install only if you are comfortable with the agent making limited operational changes to OpenClaw automatically. Require the agent to show the exact restart, cleanup, or config change before applying it, especially on production systems.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly permits automatic system-modifying actions such as session cleanup, service restarts, and configuration tuning without requiring a clear user-facing confirmation at execution time. Even if described as low-risk, these actions can disrupt service, alter behavior unexpectedly, or compound an incorrect diagnosis during an incident, especially because the skill is designed to act after failures when system state may already be unstable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.