humanizer-cn

Security checks across malware telemetry and agentic risk

Overview

This is a small, markdown-only Chinese text rewriting skill whose behavior matches its stated purpose and shows no hidden scripts, network use, credential handling, or persistence.

Install this only if you want a Chinese prose rewriting assistant. Invoke it explicitly, preferably with /humanizer-cn, and review outputs against the original because rewriting can change tone, nuance, attribution, or meaning. Avoid using it on sensitive, legal, academic, compliance, or authorship-critical text unless you are prepared to verify every change.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger phrase includes very broad natural-language wording such as “去除 AI 痕迹/去除 AI 写作痕迹”, which closely overlaps with ordinary user editing requests. In an agent environment, this can cause accidental invocation on normal conversation content, leading the skill to rewrite user text unexpectedly and override user intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal