ClawHub
Back to skill

Security audit

SEO Keyword Density

Security checks for vulnerabilities and agentic risk

Overview

This skill gives SEO keyword-density and page-audit editing guidance without hidden execution, credential access, persistence, or unrelated data handling.

Install only if you want an agent to help edit page copy and SEO metadata for keyword-density goals. For audit-only use, tell the agent not to modify files until you approve the proposed changes, because the skill's workflow includes applying edits.

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
91% confidence
Finding

The trigger phrases are very broad and map to common SEO requests such as 'SEO优化' and 'SEO检查', which can cause the skill to activate in many normal conversations without clear boundaries. Because the skill then pushes aggressive, prescriptive behavior like targeting 3-5% density and auto-expanding content, unintended activation could lead to low-quality or manipulative edits being applied when the user only asked for general advice or a limited audit.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

The skill description and operational instructions are written as if the interaction will occur in Chinese, but there is no note that the user may choose another language. That can conflict with language/locale choice policy when a skill appears to impose a language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.