ClawHub
Back to skill

Security audit

Xhs Research

Security checks across malware telemetry and agentic risk

Overview

This skill is a concise Xiaohongshu research workflow with disclosed, user-directed publishing steps and no executable payload.

Install only if you intend to use Xiaohongshu research and optional publishing workflows. Review generated drafts carefully before running any `--publish` command, confirm the target account and visibility, and ensure the external Xiaohongshu tools are configured with only the access you are comfortable granting.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill metadata explicitly says it supports publishing back to Xiaohongshu, but the document does not clearly warn that this can post content to the user's account or cause public-facing changes. In an agent setting, omission of an explicit confirmation and consequence warning increases the risk of unintended publication, reputational harm, or accidental disclosure.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The daily briefing workflow includes a final `--publish` step after a draft check, but it still lacks an explicit safety warning that this action will post through the user's account and create external side effects. Because the workflow is operational and action-oriented, an agent or user may treat publishing as routine automation, increasing the chance of accidental posting of incorrect, sensitive, or noncompliant content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.