ClawHub
Back to skill

Security audit

Memory Radar Free

Security checks across malware telemetry and agentic risk

Overview

This skill looks like a memory-file scanner, but the package is incomplete and gives conflicting guidance about local-only operation versus API key use.

Review before installing. Do not run the documented commands as-is unless the publisher provides the missing scripts and clarifies whether memory contents are processed locally or sent to an external model/API. Avoid configuring API_KEY for this skill until that trust boundary is explicit.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The documentation makes conflicting security claims: it promises a pure local, zero-network free mode, yet later states an external LLM API is mandatory and instructs users to configure an API key. This can mislead users into exposing secrets or assuming sensitive memory content never leaves the machine when the actual deployment may depend on remote services.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.