ClawHub
Back to skill

Security audit

SEO Expert Knowledge Base

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only SEO guidance skill whose website-analysis and monetization advice fits its stated purpose, with no hidden execution, persistence, or credential handling found.

Install this if you want SEO/GEO strategy help. Treat its market, pricing, backlink, and platform recommendations as advisory and verify current SEO rules, tool pricing, and regional assumptions before spending money or changing a live business site.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases include broad requests like "analyze this website" and general SEO/ranking questions that can overlap with common web-help, marketing, or even site-diagnosis requests. Over-broad activation can cause the skill to be selected outside its intended scope, leading to inappropriate tool use, misleading advice, or unnecessary exposure of user-provided website/business data to a specialized workflow.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/12-practical-tips.md (reported line 24)May include surrounding context.

md
- ❌ Multi-language switching via JavaScript
- ❌ Keyword stuffing
- ❌ PBN-style link building
- ❌ Completely relying on AI-generated content without verification

---

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The statement "Western users have high hourly wages and are willing to pay" embeds a region-specific assumption in natural-language guidance. Because the file does not explain that this advice is intentionally limited to a specific market context, it can conflict with language/locale policy expectations requiring documented justification for locale-specific constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
31% confidence
Finding

SQP-3 only covers natural-language policy violations such as language or locale policy issues. This file does not appear to force a specific user language or locale, and most content is SEO case-study material. The cited lines are not a strong policy violation, so this should likely not be treated as a finding.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The instruction 'Commit to going global' is natural-language guidance that pushes a specific locale/language direction as a general rule. Because the document does not mention user opt-in, multilingual alternatives, or cases where local-language markets are appropriate, it can be read as forcing a particular locale strategy without choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Line L081 recommends a China-specific content strategy using Chinese platforms and indexes ('Chinese index', 'Zhihu, CSDN, Juejin content matrix') as a general platform tactic. This is a natural-language locale policy concern because it imposes a specific regional/language context without stating that it is optional, region-specific, or intended only for Chinese-language audiences.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.