ClawHub
Back to skill

Security audit

聊天助理

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese dating/chat reply helper with local phrase scripts and no evidence of hidden access, persistence, network use, or destructive behavior.

Install this if you want a Chinese-language dating/chat-response helper. Be aware its trigger wording is broad, so hosts should route it only when the user is clearly asking for romantic or interpersonal message help; treat its interpretations as suggestions, not facts, and use the advice respectfully.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill description includes broad trigger phrases like '怎么回复','怎么回','聊天卡壳','聊天助手', which overlap with many ordinary conversation-assistance requests. This can cause the skill to activate in situations beyond the author's intended scope, increasing the chance of inappropriate routing, unintended persona shaping, or manipulation of general chat behavior.

Vague Triggers

Medium
Confidence
97% confidence
Finding
The instruction '直接发给我，不用记任何命令！' makes invocation effectively commandless, leaving activation scope ambiguous. In an agent ecosystem, this increases the risk that normal user conversation will unintentionally trigger the skill, causing overreach into unrelated interactions and making policy or tool routing harder to control.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.