ClawHub
Back to skill

Security audit

OpenClaw SEO Skill

Security checks across malware telemetry and agentic risk

Overview

This SEO skill is coherent and purpose-aligned, with disclosed website fetching and user-confirmed SEO code/config edits.

Install this if you want an agent to help audit and fix website SEO. Before running active audits, name the exact site or repository to inspect; before applying fixes to robots.txt, canonical tags, redirects, schema, llms.txt, or pricing pages, review the proposed diff because these changes can affect indexing and traffic.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to perform live website fetching and network-based analysis (for robots.txt, sitemap.xml, PageSpeed, headers, and browser-rendered inspection) but does not declare any corresponding permissions. That creates a capability/permission mismatch that can lead to silent overreach, unexpected external requests, and reduced operator awareness of what the skill is allowed to do.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The README uses broad natural-language trigger phrases such as asking the AI to audit or optimize a site, which can cause the skill to activate in situations broader than the user intended. In agent environments with automatic routing, ambiguous triggers can lead to unplanned access to repository files, site configs, or changes being proposed/performed under the wrong context.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The README states that after producing findings, the agent can 'directly modify code/configuration' without prominently warning about risk, review, backup, or approval requirements. In a repository-integrated agent workflow, this can normalize unsafe autonomous edits to production-sensitive assets like robots.txt, canonical tags, redirects, or structured data, potentially causing outages, deindexing, or integrity issues.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger list is very broad and includes generic complaints and common technical terms such as traffic drop, not indexed, page speed, H1, schema, and keyword research. This can cause the skill to activate in contexts where the user did not intend a network-capable SEO audit, increasing the chance of unnecessary external access, scope creep, or inappropriate advice being applied to unrelated tasks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.