ClawHub
Back to skill

Security audit

Ai Seo

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only AI search optimization skill with disclosed, purpose-aligned guidance and no executable code.

Safe to install as guidance-only material. Before using it, make sure any local product-marketing context file does not contain secrets, and review suggested robots.txt changes with the site owner because allowing AI crawlers can affect how public content is accessed, trained on, or cited.

SkillSpector

By NVIDIA
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
92% confidence
Finding
The eval explicitly rewards the skill for 'triggering on casual phrasing' without adding boundaries that the request must still be specifically about AI search visibility. That can cause over-broad activation, where general SEO or marketing requests are misrouted to this skill and receive incomplete or incorrect guidance. In this skill’s context, that is meaningfully risky because the metadata already contains a very wide trigger vocabulary and only one eval checks proper deferral to traditional SEO.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.