公众号贴图 / 九宫格多图推送

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:41 PM UTC
• Version:
  1.0.23

Overview

This skill is a disclosed WeChat image-post workflow that uses sensitive credentials and external services, but its behavior matches its stated purpose.

Install only if you intend to use the aiworkskills WeChat publishing suite. Protect aws.env, verify the companion image and publish skills before using credentials, review generated images and draft settings, and require explicit confirmation before anything is uploaded or published to WeChat.

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: 91% confidence
• Finding: The skill advertises very broad trigger phrases such as common requests to 'post some images' or 'just send pictures,' which can cause accidental invocation outside the intended workflow. In an agent ecosystem, overbroad routing can unintentionally expose user content to external image-generation or publishing flows and increase the chance of unintended actions.

VirusTotal

66/66 vendors flagged this skill as clean.