WeChat Article Extractor

• Outcome: Review
• Latest audit: May 29, 2026 at 9:32 PM UTC
• Version:
  1.0.0

Overview

The skill mostly matches its WeChat article extraction purpose, but it needs review because it can execute JavaScript taken from fetched or supplied article HTML and includes an under-documented helper with hard-coded local file paths.

Install only if you trust the publisher and can run it in a constrained environment. Avoid feeding it untrusted HTML or sensitive/private article links until dynamic JavaScript evaluation is removed or sandboxed, hostname validation is tightened, dependencies are updated, and convert.js is removed or changed to use explicit user-provided paths.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

Low

• Confidence: 82% confidence
• Finding: The skill is network-oriented and may fetch remote content from user-supplied URLs or process provided HTML tied to external sources, but the documentation does not clearly warn users about outbound requests and related privacy implications. In agent settings, lack of transparency about network access can lead users to expose sensitive URLs, tokens in query strings, or private article content without informed consent.

Known Vulnerable Dependency: qs==6.15.0 — 1 advisory(ies): CVE-2026-8723 (qs has a remotely triggerable DoS: qs.stringify crashes with TypeError on null/u)

Low

• Category: Supply Chain
• Confidence: 97% confidence
• Finding: qs==6.15.0

VirusTotal

65/65 vendors flagged this skill as clean.