ClawHub

wechat daily report

Security checks across malware telemetry and agentic risk

Overview

This skill appears intended to make WeChat chat-report images, but it should be reviewed because it sends full private chat text into an AI workflow without clear privacy guidance.

Review before installing. Use only chat exports you are authorized to process, redact names, secrets, and sensitive messages before AI analysis, prefer a local or approved AI provider, and delete generated chat-text and report artifacts when no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The Japanese description materially contradicts the skill’s stated purpose by describing weather-forecast analysis rather than WeChat group chat daily report generation. This can mislead users or reviewers about what data the skill processes and what output it creates, increasing the risk of improper consent, misuse, or failed security/privacy review for a chat-record processing tool.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs users to export full WeChat group chat text into `simplified_chat.txt` and then provide it to an AI for downstream analysis, but it does not warn about privacy, consent, retention, or sensitive personal data exposure. Group chats commonly contain personal information, private discussions, identifiers, and third-party data, so sending the full transcript to an AI service can create unauthorized disclosure and compliance risks.

Vague Triggers

Low
Confidence
91% confidence
Finding
The description is overly broad and does not define when the skill should activate or what specific inputs it is allowed to process. In an agent environment, this can cause the skill to be invoked on unintended content, increasing the chance of over-collection or processing of sensitive chat data beyond the user's intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal