Barbie Style Generator

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:33 PM UTC
• Version:
  1.0.0

Overview

This is a small image-generation skill that sends prompts and a user-supplied Neta token to an external API, with no evidence of hidden persistence or unrelated access.

Install only if you are comfortable sending prompts, optional reference image UUIDs, and a Neta API token to api.talesofai.com. Use a dedicated low-scope token if available, avoid sensitive personal data in prompts, and prefer an environment variable or short-lived token over typing a long-lived secret directly into command history.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 83% confidence
• Finding: The skill declares only Bash tooling while analysis indicates network capability, yet there is no explicit permission declaration warning users that prompts, tokens, and possibly reference identifiers will be sent off-platform. This creates a transparency and consent problem and can lead to unintended data exposure when the skill is invoked in environments that rely on declared permissions for trust decisions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence
• Finding: The documented behavior says the skill uses the Neta API, but static analysis reports that it actually contacts api.talesofai.com and supports reference-asset inheritance not fully disclosed in the description. That mismatch is dangerous because users may provide API tokens or proprietary prompts under false assumptions about the recipient and processing of their data, increasing the risk of credential misuse, privacy violations, and deceptive exfiltration to an unexpected third party.

VirusTotal

64/64 vendors flagged this skill as clean.