Back to skill

Security audit

小红书登录

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a real Xiaohongshu login-helper task, but it handles a sensitive login QR code in ways users should review before installing.

Review this skill before installing. It is not clearly malicious, but the login QR code can grant account access, and this skill saves it to a predictable local file and may send it over Feishu. Only use it if you trust the MCP service and messaging destination, and prefer changing it to use a temporary private file, explicit confirmation before sending, and automatic cleanup after login.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:27
Finding

Unvalidated Authentication QR Data Written to a Predictable Path and Optionally Transmitted

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs writing the login QR code to a fixed local filesystem path without warning the user that it will create or overwrite a file. Persisting a login artifact on disk increases the chance of unintended disclosure, stale sensitive files, or misuse by other local processes.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill's stated purpose is handling Xiaohongshu login, but it adds an external messaging step to transmit the login QR code via Feishu. That expands data exposure beyond the core authentication flow and can leak a sensitive login artifact to unintended recipients or third-party systems.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill describes sending a login QR code image through Feishu without any privacy or security warning. A login QR code is a sensitive authentication artifact, and transmitting it through messaging can expose account access to unintended viewers, message retention systems, or compromised integrations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.