ClawHub
Back to skill

Security audit

Max Content Machine

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly built to automate affiliate content publishing, but it can run unattended production deployment and cache purges using Cloudflare credentials without clear safety gates.

Install only if you intend to let an agent publish to a real site. Use a staging site first, require human approval before production deploy or cache purge, store Cloudflare credentials outside repo files and prompts, and restrict the token to the minimum zone/actions needed.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly includes an automated deployment stage followed by sitemap updates and cache purges against a live Cloudflare-backed site, but it provides no safety warning, approval gate, or scope restriction. In an autonomous agent setting, that omission increases the chance of unintended live-site modification, publishing bad content, or operational disruption if the pipeline is misconfigured or triggered on unreviewed outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The setup instructions tell users to configure a Cloudflare API token but do not mention secure secret handling, least-privilege scoping, or avoiding token exposure in files, logs, and prompts. In a skill that uses Bash and deployment tooling, poor credential guidance can lead to accidental leakage or overprivileged tokens being used by autonomous agents, enabling unauthorized site changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.