ClawHub
Back to skill

Security audit

openclaw-migration

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward migration checklist for renaming Clawd to OpenClaw, with no hidden code, persistence, network behavior, or credential handling.

Install this only in the Clawd/OpenClaw repository context. Before using it to move or remove directories, work on a branch, preview repository-wide replacements, run the listed tests and lint checks, and keep the old directory until the new layout is verified.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The playbook directs potentially destructive actions such as renaming the application root, copying contents, updating references globally, and removing or archiving the old directory, but it does not require backups, dry runs, review checkpoints, or explicit human confirmation. In an automated or semi-automated agent setting, this increases the risk of accidental data loss, broken builds, and widespread unintended changes across the repository.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger section is broad enough that the skill may activate on generic terms like "migration" or "rename" without strong repository- or task-specific constraints. That can cause an agent to apply this migration playbook in unrelated contexts and suggest or perform repository-wide renames or file moves that are inappropriate for the user’s actual intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.