ClawHub
Back to skill

Security audit

Geo Fix Schema

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed schema-markup helper that analyzes user-provided websites and generates JSON-LD without requesting credentials, persistence, or destructive authority.

Install only if you trust the external package source. Use this skill on websites you intend the agent to access, avoid private or internal URLs unless deliberate, and review the generated JSON-LD before deploying it.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
80% confidence
Finding
The skill directs the agent to fetch and analyze user-supplied URLs, which creates network-access and privacy exposure without clearly warning the user or requiring confirmation. This can enable unintended access to internal, sensitive, or user-specific endpoints if the runtime permits arbitrary outbound requests, making it an SSRF-adjacent risk in agent environments.

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
SKILL.md:39