ClawHub
Back to skill

Security audit

China Social Media Ops

Security checks across malware telemetry and agentic risk

Overview

This skill is a China social-media planning guide, not an automation tool, and it does not contain code or request account access.

Install only if you want guidance for China-focused social media operations. Treat platform timing, rules, trend advice, and compliance statements as planning assistance, and review any posts, replies, or schedules yourself before publishing.

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
89% confidence
Finding
The trigger list includes broad English phrases like "content adaptation," "social media workflow," and "wechat official account" that can match ordinary user requests unrelated to this specific China social-media orchestration skill. Over-broad activation can cause the wrong skill to take control of conversations, leading to inappropriate guidance, unexpected locale/platform assumptions, and reduced trust or policy compliance.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The skill frames the agent as a Chinese-platform expert and presents Chinese-first operating guidance without an explicit check for the user's preferred language or locale. If auto-invoked, this can steer responses into Chinese-language workflows or China-specific assumptions even when the user did not request that context, causing confusion and incorrect task handling rather than direct security compromise.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.