Security audit

Openwechat Homepage Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only helper for creating and publishing a public homepage or identity card, with disclosed but privacy-sensitive upload and hosting behavior.

Install only if you want an agent to help create and publish a public identity-card page. Before upload or deployment, inspect the generated HTML, remove sensitive personal data, confirm the exact server or hosting provider, and ensure the token is used only for the intended upload request.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (6)

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The README encourages uploading homepage data to an openwechat-claw server and to public hosting platforms, but it does not clearly warn users that the content may become visible to other users or the general public. Because identity-card style pages often contain names, avatars, bios, and links, users may unintentionally disclose personal information they did not expect to publish.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The usage and target-selection sections describe deployment to GitHub Pages, Netlify, Vercel, and Cloudflare Pages as normal workflow options without an explicit notice that these platforms typically expose content publicly. In the context of a skill designed to create identity/homepage cards, this omission increases the chance of accidental public disclosure of profile data and links.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The documentation states that uploaded homepages become visible to other IM users, but it does not clearly warn that this is public exposure of user-supplied content and may reveal personal data. In a skill specifically intended to create identity cards/homepages, users are likely to upload profile information, so omission of a privacy warning materially increases the risk of unintended disclosure.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The file explicitly documents unauthenticated public access to `GET /homepage/{user_id}` without any safety guidance about discoverability, indexing, or exposure of personal content. Because this skill is for publishing a personal homepage/identity card, the context makes the missing warning more dangerous: the expected content is identity-related and therefore privacy-sensitive.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill explicitly instructs the agent to read `base_url` and `token` from user config and use them for a network upload, but it does not require explicit user consent, display the destination, or warn that credentials and homepage content will be transmitted to an external service. In an agent setting, this creates a real risk of silent credential use and unintended data exfiltration, especially if config files contain sensitive tokens or if `base_url` is attacker-controlled.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The document explicitly encourages publishing an identity-card-style page to a public free hosting site, but it does not warn users that any personal details included will become publicly accessible and indexable. In the context of a skill for creating a personal homepage/identity card, this omission increases the risk of privacy leakage, doxxing, scraping, phishing, and impersonation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.