Learn Anything Pro

• Outcome: Review
• Latest audit: May 29, 2026 at 9:23 PM UTC
• Version:
  1.0.0

Overview

This is mostly a simple learning-resource skill, but it publicly includes a secret-like API key tied to paid per-call use, making billing and account authority unclear.

Review before installing. The skill itself is not executable and its learning-resource behavior is coherent, but the publisher should remove and rotate the exposed key and clearly explain how paid calls are authorized. Do not rely on or reuse the embedded key.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (2)

Intent-Code Divergence

High

• Confidence: 99% confidence
• Finding: The skill embeds a plaintext API key while presenting itself as a simple learning-resource recommendation tool, which creates a direct credential exposure risk. Anyone who can read the skill can reuse the key to make unauthorized calls, incur charges, consume quota, or abuse the associated external service under the owner's account.

Ssd 3

High

• Confidence: 100% confidence
• Finding: A hardcoded API key is exposed in plain text in the skill description, which is a textbook secret-leak vulnerability. Because the skill is public-facing documentation, the context makes this more dangerous: the credential is trivially harvestable and can be reused immediately for unauthorized access, billing abuse, or service impersonation.

VirusTotal

61/61 vendors flagged this skill as clean.