ClawHub
Back to skill

Security audit

Nexez Agent Discovery

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for Nexez marketplace discovery, but its unrestricted API base URL override could redirect checkout or negotiation details to a non-Nexez endpoint.

Before installing, check whether NEXEZ_BASE_URL is set and make sure it points to the intended Nexez endpoint. Do not approve checkout, negotiation, or contact-detail sharing unless the agent clearly shows the business, offer, data being sent, and destination. Use pinned SDK versions if following the optional install examples.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:8
Finding

Unrestricted API Base URL Override Can Redirect Sensitive Requests

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
references/examples.md:115
Finding

Third-Party SDK Installation Instructions Use Unpinned Versions

Content
View full analysis
Remediation
View remediation

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
Confidence
75% 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.

Content

Scanner excerpt · references/examples.md (reported line 18)May include surrounding context.

md
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:

Static analysis

No suspicious patterns detected.