Back to skill

Security audit

小红书图文自动发布引擎 Pro

Security checks for vulnerabilities and agentic risk

Overview

The skill’s social-media automation purpose is clear, but it can create persistent schedules and operate a Xiaohongshu account with broad triggers and limited user-control safeguards.

Review this skill before installing. Use it only if you want Xiaohongshu account automation, and require explicit approval before it writes schedules, creates cron jobs, opens a logged-in account, submits posts, or collects analytics. Confirm how to list, pause, and delete scheduled tasks and saved content plans.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough to activate on ordinary requests like '帮我写小红书' or '发小红书', which could load an automation skill when a user only wanted drafting help. In this skill, unintended activation is more dangerous because the capability set includes browser automation, scheduling, file persistence, and post-publication actions, increasing the chance of surprise automated behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill describes writing schedules to local storage, creating cron jobs, opening and operating a Xiaohongshu account in the browser, and returning later to collect engagement metrics, but it does not clearly disclose these persistent and account-affecting behaviors to the user at the point of use. This is risky because users may unknowingly authorize ongoing automated actions, local retention of content plans, and monitoring of account activity, which can create privacy, consent, and platform-compliance issues.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.