内置插件使用说明/手册

Security checks across malware telemetry and agentic risk

Overview

This is a read-only guide for querying local OpenClaw plugin information, with no evidence of hidden persistence, data exfiltration, or destructive behavior.

Install only if you want an agent to query your local OpenClaw plugin catalog. Use a trusted openclaw binary on PATH, and expect answers to include local plugin status, diagnostics, capabilities, and documentation excerpts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the agent to execute shell commands and read local reference files, but it does not declare corresponding permissions. This creates a trust and policy gap: the platform or reviewer cannot reliably understand the skill's required capabilities, and an agent may be induced to access local files or invoke CLI tools without explicit approval boundaries.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documentation advertises a high-privilege phone-control plugin that can temporarily enable camera, screen recording, and write actions, but it does not include an explicit warning about privacy, consent, or potential data-impact risks. In a plugin guide, this omission is security-relevant because users may enable or invoke the capability without understanding that it can access highly sensitive device functions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal