Redbook Browser Ops

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only Xiaohongshu publishing helper with disclosed account actions and explicit publish confirmation safeguards.

Install only if you are comfortable letting an agent operate the official Xiaohongshu creator site in your browser. Review the logged-in account, post text, images, and any replies carefully, and give explicit publish or reply instructions only when you intend the account action to happen.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger description uses broad example phrases like '发小红书/发笔记/保存草稿/立即发布/回复评论/看数据' without clear activation boundaries, which can cause the skill to invoke on ambiguous user requests. In a browser automation skill with posting and reply capabilities, over-broad triggering increases the chance of unintended account actions, including drafting, publishing, or interacting with comments when the user did not clearly intend to invoke this specific automation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal