小红书发布

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only helper for drafting and posting Xiaohongshu content, with user confirmation required before publishing.

Install this only if you want an agent to help operate Xiaohongshu publishing in your browser. Before approving any final action, verify the account, content, title, generated image style, and whether the agent is saving a draft or publishing publicly.

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: 89% confidence
Finding: The trigger phrases are very broad everyday expressions such as '发小红书' and '帮我发小红书文案', which can easily overlap with normal conversation and cause unintended skill activation. In a skill that performs publishing actions to a real social-media account, accidental invocation increases the risk of unauthorized posting, workflow confusion, or acting on incomplete user intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal