ClawHub
Back to skill

Security audit

Nexez Agent Discovery

Security checks for vulnerabilities and agentic risk

Overview

This Nexez marketplace helper is disclosed, scoped to explicit Nexez requests, and requires approval before checkout, negotiation, contact, payment, or booking actions.

Before installing, understand that searches and dry runs may send your request details to Nexez. Only approve real checkout, negotiation, payment handoff, or sharing contact details after reviewing the exact business, offer, price or budget, and details being sent. Be cautious if setting NEXEZ_BASE_URL because it changes the destination for requests.

SkillSpector

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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
1. Search `/api/agent-search?q=commercial%20bathroom%20plumbing%20repair&location=Chicago%2C%20IL&limit=10`.
2. Fetch `agent.json` for top relevant results.
3. Prefer Chicago/service-area matches.
4. Do not start checkout or contact sellers without approval.

Good response:
Confidence
22% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.