Seo Audit

Security checks across malware telemetry and agentic risk

Overview

This is a coherent SEO audit guide with expected notes around reading local marketing context and using SEO scraping tools.

Install this if you want an agent to run structured SEO audits. Before using it, check any local product-marketing context files for sensitive information, use trusted Firecrawl or SEO tooling, and only submit URLs or analytics context you are comfortable having analyzed.

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 (2)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill’s trigger criteria are unusually broad and explicitly include vague phrases like 'help with SEO' or 'my SEO is bad,' which can cause the skill to activate in situations where the user did not clearly request an audit. Over-broad activation increases the chance of unintended tool use, unnecessary data collection, or steering the conversation into a workflow that reads project files or external resources without sufficiently specific user intent.

Missing User Warnings

Low

Confidence: 90% confidence
Finding: The skill instructs the agent to read local context files such as .agents/product-marketing-context.md before asking questions, but it does not require notifying the user or obtaining consent for accessing project files. Even though the file is likely relevant, silent local file access can expose sensitive internal business, marketing, or roadmap information beyond what the user intended to share in the current interaction.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal