AI Content Generator Pro

• Outcome: Review
• Latest audit: May 29, 2026 at 9:26 PM UTC
• Version:
  1.0.1

Overview

This looks like a paid prototype marketed as a finished AI content tool, with overbroad permissions and unsafe API-key display behavior.

Review this before installing or paying for it. Treat it as a prototype, avoid storing real API keys until config output masks secrets, and grant permissions only if the publisher narrows or justifies the exec and web access.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The listing emphasizes 'Local Storage' and privacy while also instructing users to configure third-party API keys for OpenAI and use external AI models, but it does not clearly warn that prompts and generated content will be transmitted to those providers. This can mislead users into believing all processing is local, creating a privacy and data-handling risk for sensitive business or personal content.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill advertises sending prompts and content to OpenAI, Anthropic, and xAI, but it does not clearly warn users that their input and possibly sensitive business data will be transmitted to third-party AI providers. In a content-generation tool, users may submit proprietary drafts, marketing plans, customer information, or internal documents, so omission of this privacy disclosure can lead to unintended data exposure and compliance issues.

Missing User Warnings

Low

• Confidence: 90% confidence
• Finding: The skill highlights local storage as a privacy advantage but does not warn that generated content, prompts, or source material may remain on disk in sqlite storage. On shared systems or developer workstations, this can leave sensitive drafts, client materials, or proprietary content accessible longer than users expect.

Missing User Warnings

Medium

• Confidence: 99% confidence
• Finding: The `config show` path returns the full configuration object verbatim, which includes stored API keys for OpenAI and Anthropic. Any user or process able to invoke this command can recover secrets, leading to credential theft, unauthorized API usage, billing abuse, and possible access to downstream data handled by those providers.

VirusTotal

65/65 vendors flagged this skill as clean.