Weixin Article Reader

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:33 PM UTC
• Version:
  0.1.1

Overview

This skill is a purpose-matched Weixin article extractor that fetches a user-provided article link and returns parsed text, with no evidence of credential access, persistence, or destructive behavior.

Install if you are comfortable with the agent making outbound requests to Weixin article URLs you provide. Use genuine mp.weixin.qq.com links, and review future versions if they add broader domains, credentials, storage, or automatic publishing behavior.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill instructs the agent to fetch content from external mp.weixin.qq.com URLs via a bundled script, which is a network-capable behavior, but the skill metadata does not declare that permission. Undeclared network access weakens policy enforcement and auditability, and could lead to unexpected outbound requests or broader misuse if the script is modified or invoked on attacker-controlled inputs.

VirusTotal

62/62 vendors flagged this skill as clean.