ClawHub
Back to skill

Security audit

CLI Agent Bridge for OpenClaw

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only documentation package for a local CLI bridge, and it does not ship executable code or hidden runtime behavior.

Installing this ClawHub artifact should only add documentation. Before deploying the separate local full package it references, review that local PowerShell/runtime code separately, because that unbundled package would mediate local CLI execution and workspace file access.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Intended approval rules in the local full package

No approval intended:

- AI-only execution
- `read`
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
In the local full package:

- `read`, `list`, and `exists` are intended to run without approval
- `mkdir`, `write`, and `append` are intended to require explicit approval

## Important note
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.