ClawHub
Back to skill

Security audit

Wordpress Seo Autopilot

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malicious, but it asks for powerful WordPress and SEO-tool access while giving broad bulk-change examples without firm confirmation limits.

Install only if you are comfortable granting the agent access to modify your WordPress site. Use least-privilege application passwords, prefer a staging site first, require previews and backups before bulk edits, and explicitly set batch limits and confirmation steps for any automated workflow.

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
Confidence
93% confidence
Finding
The quick-start section exposes broad, high-privilege natural-language triggers such as auditing a site, bulk-optimizing recent posts, and setting up automated workflows without requiring explicit confirmation, scope limits, or safe preconditions. In a skill that claims direct WordPress REST API and plugin integration, these prompts could cause unintended large-scale reads or writes if an agent auto-activates on similar user phrasing, especially for bulk content modification tasks.

Static analysis

No suspicious patterns detected.