Security audit

SEO Audit Report

Security checks for vulnerabilities and agentic risk

Overview

This SEO audit skill appears purpose-built, but it can make unrestricted live web requests from the agent environment without safeguards against private or internal targets.

Install only if you are comfortable with the agent making live HTTP requests from its own environment. Use it only on sites you own or are authorized to test, avoid private or internal URLs, and choose report output paths carefully because --output can overwrite files.

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/seo_audit.py:115
Finding: Unrestricted Server-Side URL Fetching Enables SSRF
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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 94% confidence
Finding: The skill documents network access to arbitrary URLs and report generation to an output file, but it does not declare any tool scope or permissions boundaries. This creates a capability/consent mismatch: an agent or reviewer may invoke the skill without realizing it can make outbound requests and write files, increasing the risk of unintended scanning, SSRF-like access to internal resources, or unexpected filesystem changes.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The skill description and usage examples do not warn that running an audit will actively crawl external websites and send HTTP requests to the supplied target. This can lead to unintentional third-party interactions, surprise traffic generation, or accidental probing of sensitive/internal endpoints if a user supplies such URLs.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This code performs a file write via Path(args.output).write_text(report), which can overwrite or create files on disk. While the operation is somewhat implied by the --output argument, there is no confirmation prompt or explicit warning comment/docstring near the write to disclose that a filesystem modification will occur.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.