Openapi Spec Generator

• Outcome: Review
• Latest audit: Jun 18, 2026 at 6:04 AM UTC
• Version:
  1.0.0

Overview

This skill is a local OpenAPI helper, but its bundled script is mostly a canned demo while the documentation presents it as a real generator and validator.

Review this carefully before installing. It does not appear to steal data or run hidden background tasks, but it should be treated as a demo-quality tool rather than a reliable OpenAPI generator or validator. Do not rely on its output for security review, production docs, or secret-redaction guarantees, and avoid pointing it at valuable output paths unless you are comfortable with overwrite risk.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Intent-Code Divergence

Medium

• Confidence: 96% confidence
• Finding: The script advertises generation from code, HAR, and PCAP sources, but both scan and infer emit hard-coded simulated endpoints and schemas regardless of input. This is dangerous because users may trust the produced spec as derived from real source material, leading to incorrect documentation, unsafe mock environments, or missed sensitive endpoints during security review.

Intent-Code Divergence

Medium

• Confidence: 95% confidence
• Finding: The validate command presents itself as OpenAPI validation but only performs grep-based counts and then prints a largely fixed PASS result with canned warnings. This can mislead users into believing malformed or incomplete specs are valid, which undermines downstream tooling, testing, and security controls that depend on accurate validation.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The generate command writes directly to a user-supplied output path using shell redirection, which will overwrite existing files without confirmation. In an agent or automation context, this can cause unintended file clobbering, especially if output paths are influenced by prompts, templates, or mistaken operator input.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The mock command creates or overwrites a derived config file at a predictable path without warning. While lower severity than code execution, this still risks accidental destruction of existing files or confusing state in automated environments where repeated runs are common.

VirusTotal

61/61 vendors flagged this skill as clean.