ClawHub
Back to skill

Security audit

SEO + GEO Content Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed SEO content-generation workflow with optional read-only keyword tracking and SERP lookup, and no evidence of hidden execution, persistence, credential theft, or destructive behavior.

Install this if you want an SEO article workflow and are comfortable with optional SERP API use and optional read-only/public keyword tracker access. Use explicit prompts such as "write article:" to avoid accidental activation, and avoid providing private sheet URLs unless you intend the agent to read that tracker.

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)

Vague Triggers

High
Confidence
96% confidence
Finding
Allowing activation when a user merely types a keyword directly is an overly broad trigger that can invoke the skill without clear intent. In a chat environment, many normal user messages could look like keywords, causing unintended execution of the full external-data/content-generation pipeline and potentially leading to unnecessary API use, unintended browsing/processing, or incorrect tool routing.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The description states the skill is 'Designed for English-language SEO + AEO + GEO content production,' which sets a language policy for outputs. The file does not offer the user a language choice, opt-in flow, or a documented justification that would limit the constraint to a region-specific use case.

Vague Triggers

Medium
Confidence
91% confidence
Finding
Ambiguous triggers like "force framework," "only block," "regenerate block," and "rewrite with framework" are insufficiently scoped and may match unrelated user instructions outside the SEO workflow. This increases the chance of accidental skill activation or mode switching, which can redirect the assistant into generating or transforming content the user did not intend to request.

Static analysis

No suspicious patterns detected.