ClawHub
Back to skill

Security audit

SEO Content Strategy Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a content-strategy guide with disclosed SEO workflow capabilities, and I found no hidden code, persistence, or deceptive behavior.

Before using integrations such as site crawling, ranking tracking, project-management sync, or CMS publishing, confirm exactly which account or site is connected and approve any external changes before they are made. Treat CMS publishing as a write action even though the skill itself contains no executable integration code.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises website crawling, ranking tracking, integrations, and direct CMS publishing without clearly warning about what data may be accessed, transmitted to third parties, or changed automatically. In an agent setting, this can lead users to authorize broad read/write actions or external data sharing without informed consent, increasing the risk of privacy, integrity, and unintended publication issues.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The phrase "Long-tail挖掘" introduces a different language unexpectedly in user-facing instructions. Because the skill does not state that it is multilingual or allow users to choose language/locale, this creates a language-policy inconsistency.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.