ClawHub
Back to skill

Security audit

Agents Plugin Marketplace

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight marketplace guide with no executable code, credential handling, persistence, or hidden authority, though its activation wording is broad and the package does not include the referenced plugin directory.

Before installing, understand that this appears to be a documentation-only marketplace pointer rather than the full plugin collection; review any actual plugins, agents, skills, or commands separately before using them, especially if they install tools, run commands, or access sensitive data.

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation guidance is overly broad: 'When the user needs agentic workflow building blocks' can match many generic requests and may cause this marketplace skill to activate unnecessarily. In a plugin marketplace that exposes many downstream agents, skills, and commands, over-activation increases the chance of irrelevant capability injection, unsafe tool suggestions, or accidental routing into higher-risk components.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Line L14 contains Chinese text in otherwise English documentation, but the file does not indicate that users may choose their preferred language or explain a locale-specific requirement. This can conflict with language/locale policy expectations when a skill implicitly mixes or forces language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.