ClawHub
Back to skill

Security audit

wangyin-zhongnian-self-media

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed single-account WeChat content workflow with draft-box publishing safeguards, though users should understand it can read local workflow files and run publishing-related commands when asked.

Install only if you intend to use this on the named WeChat account and are comfortable with it reading the listed local WorkBuddy files, using local API credentials indirectly, generating covers via the ARK provider, and pushing confirmed articles to the WeChat draft box. Treat broad phrases like "发一篇" or "做选题" carefully and confirm before any draft-box action.

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
93% confidence
Finding
The trigger list includes broad everyday phrases such as "写一篇公众号", "发一篇", "推草稿箱", and "做选题", which are likely to appear in normal conversation and can unintentionally activate a skill that performs content generation and potentially external draft-push actions. In this skill, accidental activation is more dangerous because the workflow includes filesystem access, local script execution, and a draft-publishing step, so a benign user request could be routed into a sensitive automation path without clear intent.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The manifest description is broad and advertises end-to-end content production and publishing, but it does not clearly encode concrete activation constraints, safety boundaries, or narrow invocation conditions in the manifest itself. In agent environments, vague triggering can cause the skill to be invoked in unintended contexts, increasing the chance of unauthorized drafting, publication-oriented actions, or misuse outside the intended single-account WeChat workflow.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.