ClawHub
Back to skill

Security audit

middle-aged-social-comment

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Chinese social-commentary writing skill with no executable code, persistence, credential handling, or hidden high-impact behavior.

Install this if you want Chinese WeChat-style social commentary drafting. Be aware it may apply a specific middle-aged-reader, public-account voice when invoked by broad commentary-writing prompts, so review whether that style matches your request.

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
90% confidence
Finding
The description includes broad trigger phrases such as '按公众号风格写' and '写一篇评论文章', which can cause the skill to activate for generic writing requests beyond its intended niche. This can lead to inappropriate routing, unexpected behavior, or the model applying this strong stylistic/political-social framing when the user did not explicitly ask for it.

Natural-Language Policy Violations

Medium
Confidence
85% confidence
Finding
The skill description hard-codes a Chinese-language, WeChat-public-account style and a specific demographic/locale context without stating that this should happen only when the user opts in. If auto-invoked, it may override user language preferences or produce locale-specific content that is misaligned with the user's request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.