ClawHub
Back to skill

Security audit

WeChat To Cards

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent WeChat content-adaptation helper that creates card copy and image handoffs without hidden publishing, credential use, or persistence.

Install this if you want a WeChat-specific adapter for turning reviewed articles into card packages and share copy. Before using publish_ready mode, confirm what image-rendering tools or services your agent will call and avoid providing private drafts or sensitive source material unless that processing is acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
83% confidence
Finding
This markdown file instructs the skill to 'continue generating real images and check them one by one,' which implies creating output artifacts from user-provided content. The description does not include any warning about possible data handling, model/tool usage, or privacy implications of processing and generating media from the article content.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The entire skill is written as a Chinese-only instruction set and specifies WeChat-oriented output, but it does not explicitly state that the locale restriction is intentional or provide a user opt-in/choice of language. Under the language/locale policy, forcing a specific language without user choice can be a policy violation unless the constraint is clearly documented and justified.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.