51mee Resume Diagnose

• Outcome: Pass
• Latest audit: May 29, 2026, 8:19 PM
• Version:
  1.2.1

Overview

This skill analyzes uploaded resumes with a language model and returns feedback; the main consideration is privacy, not hidden or unsafe behavior.

Install only if you are comfortable having uploaded resume contents analyzed by a model. Consider redacting unnecessary personal details before use; no executable code, credential use, persistence, or hidden behavior was observed.

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 (1)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs the system to read uploaded resume files, extract their text, and send that content to a language model without any explicit privacy notice, consent checkpoint, or data-handling constraint. Resumes commonly contain sensitive personal data such as phone numbers, email addresses, employment history, education, and location details, so silent transmission to a model can expose users to unintended data disclosure and compliance risk.

VirusTotal

66/66 vendors flagged this skill as clean.