Back to skill

Security audit

Ai Seo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent SEO auditing helper, with a disclosed but supply-chain-sensitive MCP setup command users should pin before use.

Before installing, pin @automatelab/ai-seo-mcp to a reviewed exact version where possible, verify the npm/GitHub publisher, and run the MCP server with only the filesystem, environment, and network access needed for URL-based SEO audits.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:65
Finding

Unpinned Third-Party Package Is Automatically Downloaded and Executed

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 65–83
Vulnerability Type: Unpinned third-party dependency execution
Risk Level: Medium

json
{
  "mcpServers": {
    "ai-seo": {
      "command": "npx",
      "args": ["-y", "@automatelab/ai-seo-mcp"]
    }
  }
}
json
{
  "mcpServers": {
    "ai-seo": {
      "command": "npx",
      "args": ["-y", "@automatelab/ai-seo-mcp"]
    }
  }
}

Technical Analysis

Both documented MCP configurations invoke npx with the -y option and an npm package name that has no exact version or integrity hash. Consequently, npm may download and execute whichever package release is resolved at invocation time. The effective executable can therefore change after the Skill has been reviewed.

The -y option suppresses the normal installation confirmation, reducing the opportunity for users to inspect the resolved version before execution. If the npm publisher account, package, release process, or another relevant supply-chain component is compromised, a malicious package release could execute arbitrary JavaScript under the account running the MCP host.

No evidence establishes that the currently referenced package is malicious. This finding concerns the unsafe, mutable dependency-execution mechanism documented by the Skill.

Attack Path

  1. An attacker compromises the npm publisher account, package release pipeline, or another component capable of controlling a newly resolved release of @automatelab/ai-seo-mcp.
  2. The attacker publishes a malicious release containing an installation hook, altered server entry point, or other executable payload.
  3. A user follows the Skill documentation and configures the MCP host with npx -y @automatelab/ai-seo-mcp.
  4. The MCP host invokes the command, and npx retrieves the currently resolved package without requiring interactive approval.
  5. The malicious package executes with the operating-system privileges and environment of the user running the MC ...[truncated 800 chars]
Remediation
View remediation

Remediation Suggestions

  1. Replace the floating package reference with an audited exact version, for example:
    json
    {
      "command": "npx",
      "args": ["--yes", "@automatelab/ai-seo-mcp@0.5.0"]
    }
    
  2. Prefer installing the package through a committed lockfile and running the locally installed, reviewed executable instead of resolving a package dynamically on every launch.
  3. Verify npm integrity metadata and package provenance during installation. Where feasible, record and independently validate the expected package checksum.
  4. Remove unattended -y or --yes behavior where interactive verification is practical, and instruct users to confirm the resolved package name, publisher, and exact version.
  5. Run the MCP server with least privilege in a sandbox or container. Restrict filesystem access, environment-variable exposure, credentials, and outbound network access to what the SEO auditing functionality requires.
  6. Establish a controlled update process in which new dependency versions are reviewed and tested before the pinned version is changed.
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

MCP Config Access

High
Category
Agent Snooping
Confidence
95% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

Add to your MCP config:

Claude Code (.claude/mcp.json):

json
{
  "mcpServers": {