ClawHub
Back to skill

Security audit

Qordinate - Durable lists, facts, and reminders for OpenClaw agents.

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Qordinate integration, but it gives an agent broad ongoing authority over private data, connected apps, documents, and automations without clear safeguards.

Install only if you are comfortable giving an agent broad Qordinate account access. Use a dedicated or expiring API key, connect only necessary apps, and require explicit user confirmation before deletes, overwrites, sharing, automations, reminders, or third-party app actions. Periodically review active automations, shared documents, and stored data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill exposes a single natural-language tool that can access and modify a user's documents, contacts, tasks, web search, and connected apps, but the description does not clearly warn that prompts may trigger real external actions and data access. This increases the risk of users or downstream agents invoking sensitive operations without informed consent or appropriate confirmation.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documents section explicitly states the agent can create, read, update, and delete documents, but there is no warning that deletion or overwrite operations are destructive and may be irreversible. In a natural-language interface, ambiguous prompts can easily cause unintended data loss if destructive actions are not clearly highlighted and gated.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill advertises creation of automations that run on schedules or triggers, but does not warn that such automations can continue executing after the initial prompt and may affect external systems over time. This creates ongoing risk because a single natural-language request could establish persistent behavior with delayed or repeated side effects.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.