ClawHub

快速信息查询

Security checks across malware telemetry and agentic risk

Overview

This is a read-only diagnostic skill that can reveal local system and OpenClaw details, but its behavior is disclosed and aligned with its purpose.

Install only if you want an agent to inspect and display local system and OpenClaw status. Prefer explicit module requests, review the output before sharing it, and be aware that hostnames, IP addresses, channel names, Docker state, and redacted configuration summaries may still reveal operational details.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are broad enough to match common user language like “状态”, “概览”, or “怎么样”, which can cause the skill to activate in contexts the user did not intend. Because this skill exposes local system, Docker, network, and OpenClaw configuration information, accidental invocation increases the risk of unnecessary disclosure of sensitive operational metadata even if some fields are redacted.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill intentionally gathers and prints sensitive host metadata and local OpenClaw configuration details, including hostname, IP addresses, enabled channels, service state, and agent/session names, without any explicit privacy warning, confirmation step, or scope reduction. Although it attempts to redact common secret keys, the output still reveals operationally sensitive information that can aid reconnaissance, environment fingerprinting, and follow-on attacks if shown to an untrusted requester or logged externally.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal