Openclaw Docs

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese OpenClaw documentation helper with no executable payload, though its broad activation keywords may make it appear in some unrelated chats.

Install if you want a Chinese reference helper for OpenClaw. Before running suggested commands, verify package names and review actions that install daemons, create cron jobs, restart gateways, or configure channel credentials; keep real secrets out of chat and use placeholders when asking for help.

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: 91% confidence
Finding: The trigger list is broad enough to match common words like “gateway”, “skill”, “cron”, and popular channel names, which can cause the skill to activate in unrelated conversations. Over-triggering can lead to inappropriate context injection, user confusion, and increased chance that the agent surfaces commands or operational guidance when it was not actually requested.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal