Security audit

OpenClaw Kitchen Sink

Security checks across malware telemetry and agentic risk

Overview

This official OpenClaw fixture is broad by design but its behavior is disclosed, credential-free, and aligned with testing the plugin API surface.

Install this mainly if you need OpenClaw plugin API coverage, conformance testing, or example code. Because it intentionally touches many plugin surfaces and hooks, avoid enabling it in sensitive production agent sessions unless you specifically want that fixture behavior active.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The plugin declares activation on broad capability classes (provider, channel, tool, hook, context-engine) rather than narrowly scoped events, which can cause it to load in many unrelated workflows. In a plugin that exposes a large API surface with tools, hooks, providers, and channel features, this increases the attack surface and the chance of unintended invocation, privilege exposure, or unsafe interaction paths if any downstream component is weak.

VirusTotal

60/60 vendors flagged this plugin as clean.

View on VirusTotal