ClawHub
Back to skill

Security audit

Content Management Systems

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only CMS workflow skill with a somewhat broad trigger phrase but no hidden execution, credentials, persistence, or destructive behavior.

Reasonable to install for CMS-related development. Be aware it may activate for custom admin/editor/content systems that resemble a CMS, not only named CMS platforms; users who want platform-only activation may prefer narrower trigger wording.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction to use the skill when the user is working on a content management system "or on software that behaves like one" is ambiguous and expands activation beyond clearly defined CMS contexts. This broad phrasing could cause unintended invocation for general web apps, admin panels, or content-like systems without clear boundaries or exclusion examples.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.