ClawHub
Back to skill

Security audit

SEO-Awesome

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed SEO automation guidance skill with expected analytics and publishing automation risks, but no hidden execution, exfiltration, or privilege abuse in the artifacts.

Install only if you intend to build SEO automation. Before connecting GA4, Google APIs, publishing Cron jobs, or lead forms, use least-privilege credentials, keep secrets out of chat and source control, start in staging or dry-run, set daily change limits, and keep a rollback path for live-site changes.

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
88% confidence
Finding

The skill promotes automated SEO data pipelines and later introduces GA4 API ingestion, credential handling, and storage of analytics-derived data, but earlier automation guidance does not consistently warn that site data may be sent to external services and persisted in databases. This can lead users to enable pipelines without understanding data-flow, storage, and credential-handling risks, increasing the chance of accidental exposure of analytics data or secrets.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

Although L012 says to match the user's language, later instructions prescribe Chinese-specific operation modes such as '说中文出产品', '跟AI说', and Chinese-market model/payment constraints. This creates a natural-language locale preference embedded in the skill that may steer interactions toward Chinese-language workflows without explicit user opt-in or a clear region-specific justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.