ClawHub

Knowledge Organizer

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed knowledge-base organizer that writes or syncs user-selected notes, with no artifact evidence of hidden exfiltration or destructive behavior.

Install only if you want this agent to read your selected knowledge-base folders, write notes/assets under your vault, and upload chosen note content to Feishu or Tencent IMA. Keep `OPENCLAW_KB_ROOT` scoped to the intended vault, provide IMA credentials only when using IMA sync, and leave custom endpoint variables unset unless you explicitly trust that destination.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill advertises and instructs use of sensitive capabilities including environment variables, local file reads/writes, shell execution, and network-integrated sync targets, but the metadata does not declare any explicit permissions model. That mismatch reduces transparency and enforcement, making it easier for a host or user to invoke a skill that can access secrets, modify local knowledge-base files, and send content to external services without clear permission boundaries.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal