mofang-page-builder

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:46 PM UTC
• Version:
  1.1.0

Overview

This appears to be a legitimate Magicflu/Mofang page-building skill, with sensitive but expected credential and data-editing workflows.

Install this only for Magicflu/Mofang development. Use least-privilege test accounts, prefer staging or sanitized data, keep cookies/JWTs/passwords out of source control and shared logs, and review any generated delete or publish flow before running it against real business data.

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 (4)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill includes command examples that pass usernames, passwords, and raw browser cookies directly on the command line without an adjacent warning about secret handling. This is dangerous because shell history, process listings, logs, screenshots, and copied transcripts can expose live credentials or session tokens, enabling account takeover or unauthorized access to Magicflu environments.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README explicitly suggests using a script to pull `fielddef` data from a real environment, but it provides no warning about privacy, production-data handling, access control, or the risk of copying sensitive schema/configuration into local mock folders. In a developer-facing skill that encourages local debugging and same-origin publishing workflows, this can normalize exporting live environment data into less controlled contexts, increasing the chance of inadvertent exposure or misuse.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The document explicitly instructs users to obtain JWTs via username/password, send bearer tokens, and merge Set-Cookie headers, but provides no warning about secure credential handling, token storage, log redaction, or session leakage. In the context of a code-generation skill, this can directly lead generated scripts to embed credentials insecurely or mishandle authenticated sessions, increasing the chance of account compromise or unauthorized API access.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The API summary advertises a DELETE records endpoint without any caution that it permanently removes user data or that callers should require confirmation, authorization checks, or backups. Because this skill is intended to generate CRUD/admin pages, omission of destructive-operation safeguards makes it more likely that generated tools will expose accidental or unauthorized data deletion flows.

VirusTotal

63/63 vendors flagged this skill as clean.