ClawHub
Back to skill

Security audit

SEO Companion

Security checks for vulnerabilities and agentic risk

Overview

This SEO skill is mostly transparent, but its URL audit script can be tricked into fetching internal network pages through redirects, so it needs review before use.

Use this skill only for public sites and preferably in an environment without access to sensitive internal services. Before broad installation, fix the audit script to disable automatic redirects or validate every redirect destination, and keep package installation user-approved.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/audit_page.py:138
Finding

Server-Side Request Forgery Through Unvalidated Redirect Destinations

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The code does perform part of the declared SEO auditing purpose: on-page and some technical SEO checks for a supplied URL. However, the description substantially overstates breadth and depth. There is no implementation for local SEO, GBP gaps, keyword research, backlink analysis, content strategy beyond simple word count, or any execution/remediation actions. The code also does not crawl a site broadly; it fetches one page and optionally robots.txt and sitemap endpoints. Network access to public URLs is consistent with SEO auditing, and the host/IP blocking is a supporting safety measure rather than a mismatch. Overall, the declared description is materially broader than the actual behavior.

Content

No source excerpt is available for this finding.

Cloud Metadata Access

High
Category
Server-Side Request Forgery
Confidence
90% confidence
Finding

Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.

Content

Scanner excerpt · scripts/audit_page.py (reported line 32)May include surrounding context.

python
TIMEOUT = 20
BLOCKED_HOSTS = {
    "localhost",
    "metadata.google.internal",
}
BLOCKED_IPS = {
    "127.0.0.1",

Cloud Metadata Access

High
Category
Server-Side Request Forgery
Confidence
90% confidence
Finding

Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.

Content

Scanner excerpt · scripts/audit_page.py (reported line 38)May include surrounding context.

python
"127.0.0.1",
    "0.0.0.0",
    "::1",
    "169.254.169.254",
}

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.