ClawHub
Back to skill

Security audit

Seo Keyword Researcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward SEO research helper that uses disclosed web searches and page fetches to produce an article brief, with no evidence of hidden code, persistence, credential access, or destructive behavior.

Install this if you want an SEO-oriented research workflow that will search the web and fetch competitor pages. Use it for explicit keyword or article-brief tasks, and be aware that broad content-planning prompts may route to this skill even when you only wanted general brainstorming.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises many generic trigger phrases such as 'content planning', 'keyword research', and 'article topic research', which are common in ordinary user conversations and can cause unintended invocation. In an agent environment, accidental activation can lead to unnecessary web access, fetching external pages, and generation based on untrusted content, increasing both prompt-injection exposure and misrouting risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.