ClawHub
Back to skill

Security audit

OpenClaw Debug

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward OpenClaw troubleshooting helper that searches official resources and GitHub issues, with only minor privacy and scope cautions.

Before using this skill, redact tokens, private URLs, tenant names, proprietary configuration, and long stack traces from any troubleshooting details, because the workflow may search public documentation and GitHub with issue keywords.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description says to use the skill whenever users encounter OpenClaw-related issues or errors, and includes wide categories like configuration questions and version upgrade advice. It does not provide explicit exclusion conditions or negative examples, so the trigger scope is somewhat open-ended and may cause unintended invocation across broad OpenClaw support conversations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to search external documentation and GitHub issues using user-provided issue details, but it does not require minimization or user notice before sending potentially sensitive error messages, configuration fragments, or environment details to third-party services. In a troubleshooting context, users often paste tokens, internal hostnames, stack traces, or proprietary configuration, so this can lead to unintended disclosure outside the primary system boundary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.