Welight 公众号排版发布

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:26 PM UTC
• Version:
  1.0.1

Overview

This is a disclosed WeChat article formatting and publishing skill, with network and credential use tied to its stated purpose.

Install this only if you intend to let the agent fetch article URLs and use configured WeChat Official Account credentials. Use dry-run or draft mode first, review the rendered article and images before posting, and keep app credentials in a trusted config or environment.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The default prompt authorizes a broad workflow: ingesting article content, transforming it, presenting theme options, and publishing to a WeChat Official Account when prerequisites exist, but it does not define clear user-trigger boundaries or confirmation gates. In an agent setting, this increases the risk of unintended high-impact actions such as publishing or drafting content from ambiguous user input or from content pulled implicitly by the skill.

VirusTotal

64/64 vendors flagged this skill as clean.