Ai Writing Risk Review

Security checks across malware telemetry and agentic risk

Overview

This prompt-only skill reviews submitted text for AI-writing risk and shows no hidden execution, data access, or persistence.

Install only if you want a heuristic AI-writing risk reviewer. Use it on text you are allowed to analyze, avoid treating its result as proof of misconduct, and require extra evidence for academic, employment, legal, copyright, or disciplinary decisions.

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 skill description is extremely broad, covering '任意文本' and many generic intents, which can cause the platform to invoke this skill in situations far beyond its intended niche. Overbroad activation increases the chance of misrouting user requests, unintended handling of sensitive content, and interference with more appropriate specialized skills, though it does not by itself create direct code-execution or data-exfiltration risk.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal