ClawHub
Back to skill

Security audit

Netlify

Security checks for vulnerabilities and agentic risk

Overview

This Netlify skill is a broad but plainly documented Maton/Netlify administration helper with strong user-approval guidance for writes and automation.

Install only if you want a Maton-mediated Netlify administration skill. Review the OAuth scopes before connecting, prefer read-only tasks, and require explicit confirmation before any write, DNS/env-var change, member change, webhook/build-hook creation, or persistent automation.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description narrows the apparent scope of the skill to sites, deploys, builds, DNS zones, and environment variables, while the body also documents administrative capabilities for webhooks, build hooks, forms/submissions, and account membership. That mismatch can mislead an operator or upstream policy layer into granting or invoking a broader set of actions than the summary suggests, increasing the chance of unsafe use of write-capable or data-egress features.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest states that endpoints beyond the stated set require the user to ask for them by name, but the same file already includes many additional Netlify endpoints and operations. This creates a policy/documentation contradiction that can weaken guardrails: an agent may rely on the narrower promise while still having in-skill instructions for broader actions, including writes and persistent forwarding features.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.