Back to skill

Security audit

OpenClaw Workspace Initializer

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this workspace initializer benign because its reported persistent workspace and memory features appear aligned with its purpose, though the scan is incomplete and carries medium confidence.

The verdict is benign, not a guarantee of safety. Consider whether you want workspace rules or memory records to persist across sessions. The scan was partial: several referenced paths could not be matched to bundled files, and static analysis did not cover the PNG images.

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
Vulnerability Patterns
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Content

Scanner excerpt · README.en.md (reported line 22)May include surrounding context.

md
- ❌ Forget its own memory system (`memory/`), waking up amnesiac every session
- ❌ In multi-agent shared config setups, use `config.apply` to overwrite the whole `openclaw.json`, **wiping out other agents' changes**

This skill solves it all in one go: **directory structure + persistent rules + config safety**.

## Features

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Content

Scanner excerpt · README.en.md (reported line 84)May include surrounding context.

md
| | openclaw-workspace-starter | **xiaoyaoclaw-workspace-initializer** |
|---|---|---|
| Directory structure | basic template | complete convention system (7 dirs + naming rules + behavior rules) |
| Persistent rules | no WORKSPACE.md | ✅ WORKSPACE.md survives restarts |
| Multi-agent config safety | ❌ | ✅ config.patch / no config.apply (learned from real incidents) |
| Standalone templates | embedded | ✅ templates/ reusable separately |