ClawHub
Back to skill

Security audit

Neckr0ik Api Wrapper

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-built OpenAPI skill generator whose network calls, credential handling, and file creation are expected for that purpose, but users should review generated code before using it.

Install only if you want an agent to generate local OpenClaw skill/API wrapper files from OpenAPI specs. Use trusted specs, review the generated code and target base URL before running it, avoid broad credentials, and keep generated output in a dedicated directory to prevent accidental overwrites.

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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation describes capabilities that read environment variables, fetch remote OpenAPI specs over the network, and generate files on disk, but it does not declare corresponding permissions. That mismatch can hide the true security boundary from users and reviewers, increasing the risk of unexpected credential access, outbound requests, and file writes during use.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill advertises support for API keys, bearer tokens, basic auth, and OAuth, but it does not warn users that generated wrappers may process and transmit those credentials to external services. In this context, the omission matters because the tool is specifically designed to connect to arbitrary third-party APIs, so users may expose secrets without understanding the trust and data-flow implications.

Missing User Warnings

Low
Confidence
86% confidence
Finding
The skill says it generates SKILL.md, claw.json, and scripts, but it does not clearly warn that it will create and overwrite multiple local files. For a code generator, undisclosed file-writing behavior can lead to accidental clobbering of existing files or placement of generated content in unintended directories.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The generated client will send user-supplied parameters and request bodies to whatever API base URL is defined by the spec or CLI input, but the generator provides no explicit consent boundary, destination warning, or validation of where data is being sent. In the context of an auto-generated API wrapper skill, this is more dangerous because untrusted or surprising OpenAPI specs can cause operators to exfiltrate sensitive data to third-party or internal endpoints without realizing it.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.