Aihot Skill Lite

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a low-impact news or curation helper with some overbroad routing and language instructions, but no evidence of hidden access, persistence, credential use, or destructive behavior.

Install only if you want a Chinese-language news or curation assistant. Be aware it may activate eagerly on ambiguous news-related prompts and may respond in Chinese unless the skill is updated to follow the user's language preference.

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 (3)

Vague Triggers

High

Confidence: 91% confidence
Finding: The instruction '不要 undertrigger' pressures the agent toward aggressive invocation and discourages conservative routing. This increases the chance of unnecessary external requests and incorrect tool selection, especially when user intent is ambiguous.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The instruction '不要 undertrigger' pressures the agent toward aggressive invocation and discourages conservative routing. This increases the chance of unnecessary external requests and incorrect tool selection, especially when user intent is ambiguous.

Natural-Language Policy Violations

Medium

Confidence: 84% confidence
Finding: The skill mandates Chinese output without considering the user's language preference. While not a classic exploit, this can degrade usability, cause misunderstanding, and create unsafe agent behavior by overriding user-directed communication constraints.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal