薇薇发

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.0

Overview

This looks like internal testing notes for file and image upload workflows, but it exposes raw service endpoints, user/file identifiers, and an API bearer token without clear privacy or access-control boundaries.

Review before installing. Do not use this with sensitive files or images unless the publisher removes and rotates the exposed token, replaces internal endpoints and identifiers with placeholders, and clearly documents who can access uploads, how authorization is enforced, and how long uploaded content is retained.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The invocation examples are broad natural-language requests that can trigger chained weather and flight-query behavior without clear activation boundaries or user-intent validation. This increases the chance of unintended invocation, scope creep between linked skills, and misuse of the agent flow, especially because the examples combine multiple tasks and route one skill into another.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The document exposes internal upload/display endpoints, a required `currentuser` header for local debugging, and concrete file paths/user identifiers, but provides no safeguards around authentication, authorization, retention, or privacy. In this context, the skill is effectively operational guidance for handling user-supplied files and images, so omitting data-handling warnings and exposing internal service details increases the risk of unauthorized access, privacy leakage, and misuse of uploaded content.

VirusTotal

66/66 vendors flagged this skill as clean.