ClawHub
Back to skill

Security audit

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

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly provides a real Qordinate memory integration, but it gives a remote agent broad lasting access to store, change, delete, share, and automate user data without enough scoping or confirmation guidance.

Review before installing. Use a narrowly scoped Qordinate API key if available, avoid sending secrets or sensitive personal data, and require explicit confirmation before storing information permanently, deleting or sharing documents, interacting with connected apps, or creating automations.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:29
Finding

Overbroad Delegation of Persistent User Data to an External Agent

Content
View full analysis
Remediation
View remediation

SkillSpector

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 (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

md
| Field | Value |
|-------|-------|
| **Protocol** | MCP (Model Context Protocol) — Streamable HTTP |
| **MCP Server URL** | `https://api.qordinate.ai/mcp` |
| **Auth Method** | Bearer token — `Authorization: Bearer qk_YOUR_API_KEY` |
| **API Key Format** | Prefixed with `qk_` |

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill exposes a single natural-language tool, query_agent, that can perform broad read/write actions across documents, contacts, tasks, forms, automations, web search, and connected apps, but it does not warn users that free-form prompts may trigger destructive or privacy-impacting operations. Because the interface is highly permissive and abstracts multiple capabilities behind one tool, users and upstream agents may underestimate the scope of actions, increasing the risk of accidental data modification, sharing, automation setup, or third-party app interaction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.