ClawHub
Back to skill

Security audit

RAG Search

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real RAG search tool, but it relies on unreviewed local code and does not clearly disclose where user queries are processed.

Install only if you control and trust the local rag_system directory. Before use, review search_pipeline.py and embedding_client.py, confirm whether Qwen embedding or rerank calls leave the machine, and avoid sensitive queries unless that data flow is acceptable.

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 (1)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill sends user queries to embedding and reranking clients, which likely involve external or separate service boundaries, without any disclosure, consent, or sensitivity checks. If users submit confidential, regulated, or personal data, that information may be exposed to third-party services or retained outside the expected trust boundary.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.