Wechat Blog Write Publish

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:26 PM UTC
• Version:
  0.1.0

Overview

This skill clearly does what it advertises: creates WeChat articles from user materials and uploads them to a WeChat draft box.

Install this only if you intend to let the agent prepare WeChat Official Account drafts and upload the resulting content to WeChat. Review generated articles before publishing, avoid using confidential source material unless external upload is approved, and keep AppSecret credentials out of chat, logs, screenshots, and source control.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The README explicitly instructs users to publish generated content to the WeChat draft box using configured AppID/AppSecret, but it does not clearly warn that article content, media, and account-linked credentials will be used to transmit data to an external platform. In a skill that automates content generation and publishing, this omission can cause users to unknowingly send sensitive or proprietary material to a third-party service.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill explicitly directs publishing generated content to a WeChat draft box via `wenyan publish`, which causes an external network action and modifies a connected third-party account. There is no explicit requirement for a clear user confirmation or warning about account-side effects, so an agent could perform unintended publication or transmission of content to the user's WeChat environment.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill instructs use of AppID and AppSecret for WeChat configuration but does not include strong guidance to protect, avoid exposing, or avoid pasting these secrets into chat or logs. In an agent setting, this creates a real risk of credential disclosure, insecure handling, or accidental persistence of secrets in conversation history, shell history, or tool output.

VirusTotal

66/66 vendors flagged this skill as clean.