ClawHub
Back to skill

Security audit

Local Geo Writer

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed DeepSeek-backed local SEO article generator with expected external API use and no hidden persistence or destructive behavior.

Install only if you are comfortable sending the entered business details and prompts to DeepSeek or the configured compatible endpoint. Use a trusted DEEPSEEK_BASE_URL, keep the API key scoped and private, and run SEO checks only on files you intend the tool to read.

SkillSpector

By NVIDIA
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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares runtime requirements for an API key and invokes a local Python script that will necessarily read files and make outbound network requests, but it does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: a host may allow the skill to run without clearly informing users that local content and environment secrets could be accessed and transmitted to an external model provider.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The code sends user-provided business details, keywords, city, and extra context to an external LLM API without an explicit disclosure or consent mechanism at the transmission point. If users include sensitive business or personal information, that data is exported to a third party and may be retained or processed under external policies.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:56