Back to skill

Security audit

ClawHub Plugin Packager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed plugin-packaging helper with templates and review rules, and I found no hidden execution, persistence, or data-exfiltration behavior.

Install this if you want an agent to help create or audit OpenClaw plugin packages. Review generated plugins before publishing, especially any provider or channel plugin that introduces credentials, network access, or side effects.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description describes a packaging and analysis tool for creating, repairing, or auditing publish-ready plugin packages from rough requirements. The supplied code does not implement any of those behaviors. Instead, it is only a simple plugin entry template that registers a channel and returns a name. This is a materially different primary purpose, so the description does not accurately represent the code.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

There is a clear mismatch between the declared purpose and the actual code. The description claims substantial functionality around generating, repairing, and auditing publish-ready plugin packages, but the code chunk contains only a simple template function returning a placeholder configuration object. No packaging, validation, auditing, file handling, or requirements-processing behavior is present in this snippet. The actual behavior is a setup stub, which is materially different from the declared end-to-end plugin package workflow.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared description describes a higher-level tool for generating, repairing, or auditing complete publish-ready plugin packages and managing separate output artifacts. The supplied code chunk is only a simple template for a plugin entry point that registers a provider and exposes a plugin name. It does not implement packaging, repair, auditing, artifact separation, or any workflow around rough or inconsistent requirements. This is a material difference in primary purpose, so it should be flagged as a mismatch.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared purpose describes a higher-level system for producing or auditing publish-ready plugin packages, including package/critique separation. The supplied code chunk instead only provides a minimal template for a plugin entry that registers a single tool whose run function echoes user input. This is a materially different primary purpose, not merely an implementation detail. There are no package-building, repair, auditing, file-management, or critique-generation behaviors present.

Content

No source excerpt is available for this finding.