Content Adaptation for Xiaohongshu, Douyin, Bilibili, WeChat

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed content-adaptation helper that generates platform-specific copy and does not show hidden posting, credential access, persistence, or destructive behavior.

Before installing, be aware that broad phrases about sending content to a platform may activate the skill. Review generated drafts before publishing, and avoid including sensitive material if you later send cover prompts or content to external image or publishing tools.

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
95% confidence
Finding
The trigger phrase "发到XX平台" is overly broad and can match ordinary user requests rather than an intentional invocation of this skill. That ambiguity can cause unintended activation, pulling user content into the skill’s workflow and potentially spawning platform-specific generation behavior when the user did not explicitly opt in.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal