Openclaw Api Reference

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:31 PM UTC
• Version:
  1.0.0

Overview

This is a documentation-only OpenClaw API reference; it includes examples for sensitive API operations, but they are disclosed and not executed by the skill itself.

Install this as a reference document, not as an automation tool. Before running examples against a real OpenClaw instance, verify the server, protect API keys and JWTs, and treat delete, config update, webhook creation, user creation, and script-based skill creation endpoints as privileged operations that should require trusted users and review.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

High

• Confidence: 90% confidence
• Finding: The API reference explicitly documents creating a skill with a raw script field using an example shell command, but provides no warning that such content may be executed on the host. In a system that supports running created skills, this normalizes arbitrary command execution and can lead to remote code execution, persistence, or data compromise if exposed to untrusted users.

VirusTotal

63/63 vendors flagged this skill as clean.