Back to skill

Security audit

okx-cex-skill-mp

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because its documented installer uses an unpinned `npx skills` dependency, and the scan could not fully inspect all security-relevant content.

Consider delaying installation until the `skills` installer is pinned to a reviewed version and the partial scan coverage is resolved. If you proceed, verify the installer source and version, and review what the force-install option bypasses.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (7)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 171)May include surrounding context.

md
- `SKILL.md` — the skill's main instruction file

MCP server referenced without pinned version: 'npx unavailable'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The documented installation flow invokes npx skills add without specifying a version of the skills package, although this is a CLI dependency rather than an MCP server. If npx resolves and downloads that dependency, a compromised or unexpected release could execute with the user's permissions; verifying the downloaded skill does not authenticate the installer dependency.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 145)May include surrounding context.

  1. Runs npx skills add to install to all locally detected agents
  2. Records the installation (including verification status) in ~/.okx/skills/registry.json

Force-install (bypass verification):

bash
okx skill add grid-premium --force

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
85% confidence
Finding

This error-handling entry repeats the unpinned npx skills add dependency used by the installation flow. It is another reference to the same supply-chain risk at line 142, not a separate execution path or an MCP server vulnerability.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx not'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
70% confidence
Finding

Overly Broad Trigger: description clause 'Use this skill when the user asks to' activates on 'to', which is too short and may match unintended inputs

Content

No source excerpt is available for this finding.