WeChat MP Assistant

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.0

Overview

This appears to be a real social media automation skill, but it needs review because it can schedule or publish content to external accounts without clear per-action safeguards.

Install only if you intend to let the skill operate connected social accounts. Before enabling it, confirm which platforms it can post to, use draft or dry-run mode first, require explicit approval for each live publish/sync/reply action, and avoid unattended schedules until you have verified the outputs and disable path.

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 (1)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill advertises scheduled posting and multi-platform sync, which are capabilities that can modify external accounts or publish content, but it provides no warning, confirmation requirements, or safety boundaries. In an agent setting, this creates a real risk of unintended or unauthorized actions against connected social media accounts, especially if users assume the skill is limited to drafting and analysis.

VirusTotal

66/66 vendors flagged this skill as clean.