ClawHub
Back to skill

Security audit

OpenClaw Money Maker

Security checks across malware telemetry and agentic risk

Overview

This skill is transparent and instruction-only, but it encourages stored credentials, unattended scheduling, and public or paid-platform actions without enough guardrails.

Review before installing. Treat this as a monetization playbook, not something to run unattended. Prefer scoped tokens or a secret manager over plaintext passwords, protect any local credential file, disable cron or heartbeat scheduling unless you have clear limits, and require manual approval before public posts, bounty claims, task submissions, marketplace publication, or paid-platform actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs users to store API keys, usernames, and passwords in a plaintext credentials file under the home directory, without any warning about file permissions, encryption, or safer secret-management options. This increases the chance that secrets are exposed to other local users, backups, logs, or malware, leading to account takeover on the referenced external services.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The publishing and posting sections provide ready-to-run automation for creating external posts and publishing content, but do not include warnings that these actions send data to third-party services and may publish publicly. In an agent skill context, that omission can cause unintended disclosure, spammy behavior, or irreversible publication if users automate the workflow without explicit confirmation gates.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# PayAClaw - Task platform
curl -X POST https://payaclaw.com/api/agents/register \
  -H "Content-Type: application/json" \
  -d '{"agent_name":"YourAgentName","description":"Your capabilities","capabilities":["coding","writing"]}'
Confidence
84% confidence
Finding
The skill includes commands that transmit user-supplied registration data to an external domain. While external registration is expected for this skill's purpose, the lack of trust, privacy, and verification guidance means users may send identifying or capability data to third-party services without understanding the risks or validating the endpoints.

Session Persistence

Medium
Category
Rogue Agent
Content
### Step 2: Save Your Credentials

Create `~/.config/openclaw-earnings/credentials.json`:

```json
{
Confidence
97% confidence
Finding
The session persistence finding is valid because the skill recommends long-lived local storage of sensitive credentials, including an API key and a password, in a reusable file path. Persisted secrets expand the attack surface by making credential theft easier through filesystem access, accidental sync, backup exposure, or compromise of the host running the agent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.