ClawHub

Chen Memory Setup

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill helps users set up persistent memory search, but users should understand it can make notes and past conversations searchable and may use external embedding providers.

Install or follow this only if you want persistent memory. Prefer the local provider for sensitive work, avoid indexing secrets or highly sensitive personal/business data, consider disabling session transcript indexing, and periodically prune MEMORY.md and memory logs.

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 explicitly encourages indexing long-term memory, daily logs, past conversation transcripts, and user preferences, but it does not warn users that this can aggregate sensitive personal or business information into a searchable store. That omission creates a real privacy and data-handling risk because users may enable the feature without understanding the scope of collection, retention, and exposure of the indexed content.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill recommends external embedding providers such as Voyage and OpenAI and instructs users to supply API keys, but it does not disclose that memory content and session data may be transmitted to third-party services for embedding. This is dangerous because users could unknowingly send confidential conversations, preferences, or project information outside their local environment, creating compliance, confidentiality, and consent issues.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal