Security audit

LaunchRanked SEO

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent SEO and AI-search guidance skill that uses public site checks and optional signed-in LaunchRanked reports, with sensitive actions mostly disclosed and user-gated.

Install this if you want an agent to audit and modify a website for SEO or AI-search visibility. Expect it to use LaunchRanked tools against public deployed URLs, and only connect the optional signed-in reports if you are comfortable sharing account-linked SEO/visibility data with that service. Review proposed noindex, robots.txt, canonical, redirect, and URL-structure changes before applying them because those can affect search traffic.

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

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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

Findings (3)

Unvalidated Output Injection

High

Category: Output Handling
Confidence: 65% confidence
Finding: Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.
Content: Scanner excerpt · references/frameworks.md (reported line 13)May include surrounding context.
md
- **noindex**: `robots: { index: false, follow: true }`. - **Sitemap / robots**: `app/sitemap.ts` (returns `MetadataRoute.Sitemap`) and `app/robots.ts` (returns `MetadataRoute.Robots`, including `sitemap: "https://example.com/sitemap.xml"`). - **OG image**: `app/opengraph-image.tsx` (or per route segment) using `ImageResponse` from `next/og`. - **JSON-LD**: in the page component, `<script type="application/ld+json" dangerouslySetInnerHTML={{ __html: JSON.stringify(data).replace(/</g, "\\u003c") }} />`. - **llms.txt**: `public/llms.txt`, or `app/llms.txt/route.ts` returning `text/plain` if it should be generated. - **lang**: `<html lang="en">` in the root layout.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description is broadly scoped around common requests like improving SEO, fixing metadata, auditing a site, and planning launches, which can cause the agent to invoke this skill for many generic web-development or marketing queries. Over-broad invocation increases the chance of unnecessary external tool use and unintended repo modifications on deployed/public URLs, especially because the skill encourages live-site inspection and code changes.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The document repeatedly instructs implementers to set lang="en" or equivalent English locale defaults across frameworks. This is a natural-language locale policy constraint presented as a default without offering a user choice or documenting why English is required.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.