ClawHub
Back to skill

Security audit

Seo Keyword Researcher

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward SEO keyword research skill that uses public web searches and fetched competitor pages to generate article briefs, with no code execution, persistence, credential handling, or hidden behavior found.

This skill is reasonable to install for SEO content planning. Be aware that broad prompts about content planning or keyword research may invoke it and cause web searches/fetches, so use explicit wording when you do or do not want SEO research.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill advertises very broad trigger phrases such as 'keyword research', 'content planning', and 'article topic research', which can match many normal user requests beyond the narrow intended SEO-briefing use case. This can cause unintended invocation, leading the agent to run web searches and fetch external content when a user did not explicitly ask for this workflow, increasing the chance of incorrect routing, unnecessary external data access, and prompt-surface expansion.

Static analysis

No suspicious patterns detected.