小红书最夯账号(红狐数据)

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu ranking/report tool that uses a third-party public data API and writes report files, with some setup and scoping notes but no artifact-backed malicious behavior.

Install only if you are comfortable with the skill contacting redfox.hk for Xiaohongshu ranking data, creating HTML files in the workspace, and optionally creating a recurring subscription or calendar item when you ask for one. On vague ranking requests, confirm that you want Xiaohongshu data before letting it run.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill explicitly instructs the agent to make outbound network requests to a third-party API and to generate/write HTML reports, but the manifest declares no corresponding permissions. This creates a capability/permission mismatch that weakens user consent and platform enforcement, because the skill can access external data and write files without transparent declaration.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger phrases include broad, everyday expressions such as generic ranking/recommendation terms, increasing the chance that the skill activates on unrelated user requests. Over-broad invocation can cause unintended third-party requests, file generation, and forced follow-up actions like attachment delivery or subscription prompts without clear user intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal