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 sensitive but purpose-aligned advice around Google APIs, publishing, and analytics, and it includes meaningful user-control and safety caveats.

Install only if you want an SEO automation advisor. Treat GA4 credentials, Google API keys, lead data, and publishing automation as sensitive: use read-only scopes where possible, keep secrets out of chats and repositories, test in staging, require human approval before production publishing, and maintain rollback controls.

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 (3)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
Line L59 says 'speak Chinese, ship product,' which presents a language-specific workflow as the expected mode of use. Because the file does not frame this as optional or offer alternative language choices, it conflicts with the policy against forcing a specific language without user opt-in.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The non-OpenClaw installation path says to open `prompt.md`, copy the full text, and paste it into any AI, which creates an overly broad activation boundary. That can cause accidental execution of privileged instructions in unrelated assistants or contexts, especially because the skill is designed to automate publishing and content workflows.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
Line L012 says the default communication style is Chinese-oriented ("默认沟通风格") while also saying the assistant should match the user's language. This creates a mild language-policy ambiguity because the skill establishes a default locale/style preference rather than making language choice entirely user-driven.

Static analysis

No suspicious patterns detected.