中文去AI味 Pro

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:46 PM UTC
• Version:
  1.0.0

Overview

This skill is a local Chinese writing assistant whose scripts analyze user-provided text and generate rewrite prompts without hidden network, credential, or persistence behavior.

Reasonable to install for local Chinese rewriting workflows. Choose output paths carefully because the output option can overwrite an existing file, and avoid sending private drafts to an external AI service unless that sharing is intentional.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

• Confidence: 78% confidence
• Finding: The script writes to a user-supplied path using shell redirection without checking whether the destination already exists, which can silently overwrite local files if the caller makes a mistake or if the path is influenced by untrusted input. In this skill's context the danger is limited because the path is explicitly provided by the user and there is no privilege escalation, but accidental data loss is still a real integrity issue.

VirusTotal

65/65 vendors flagged this skill as clean.