Xiaohongshu

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Xiaohongshu research helper with clear limits against bulk scraping, downloads, reverse engineering, and automatic account actions.

Use this for small, user-directed analysis of public Xiaohongshu pages. Avoid using it for bulk scraping, bypassing platform controls, downloading content, or account actions; logged-in use may reveal account-specific page context to the agent.

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: 88% confidence
Finding: The description says the skill should be invoked whenever access to or automation of Xiaohongshu-related content is needed, which is broader than the skill’s own stated boundaries. Overly broad activation can cause an agent to select this skill in contexts involving automation, scraping, or account-scoped actions that may exceed intended safe use and platform-compliant behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal