ClawHub
Back to skill

Security audit

XHS Knowledge Retriever

Security checks across malware telemetry and agentic risk

Overview

This skill is a local read-oriented retriever for an existing Xiaohongshu knowledge index, with no hidden credential access, shell execution, or persistence beyond optional user-directed output.

Install only in an environment where reading the configured XHS knowledge index is intended. Be aware that sentence-transformers may use or fetch models depending on local cache state, and consider pinning dependencies or using a lockfile for repeatable installs.

SkillSpector

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

Unpinned Dependencies

Low
Category
Supply Chain
Content
numpy>=2.0.0
sentence-transformers>=5.1.0
Confidence
94% confidence
Finding
numpy>=2.0.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
numpy>=2.0.0
sentence-transformers>=5.1.0
Confidence
95% confidence
Finding
sentence-transformers>=5.1.0

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.