ClawHub
Back to skill

Security audit

SEO Article Generator

Security checks across malware telemetry and agentic risk

Overview

This SEO article skill has a coherent purpose, but it appears to use local OpenClaw credentials and recurring website file changes in ways users should review first.

Review before installing. Only use it in a website workspace where automatic article creation and sitemap edits are acceptable, and verify how it obtains the DeepSeek/API key. Prefer explicit environment-based credentials and a manual or clearly disableable schedule.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The script reads a DeepSeek API key from an unrelated external file at /home/admin/.openclaw/openclaw.json, expanding its trust boundary beyond its own configuration. This creates credential-access behavior that can unintentionally harvest or reuse secrets from another tool, which is especially risky for a content generator that does not need to inspect third-party app configs to function.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly states it will auto-create HTML files and auto-update sitemap.xml, but it does not warn users that installing or invoking it causes automatic file modifications on disk. This can lead to unexpected changes to website content and SEO infrastructure, which is especially risky because the behavior is periodic ('one SEO article per hour') and not clearly framed as a side effect requiring user awareness or consent.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.