ClawHub
Back to skill

Security audit

Agent Memory Kit

Security checks across malware telemetry and agentic risk

Overview

This is a transparent local memory and search kit, with privacy hygiene caveats but no evidence of hidden collection, exfiltration, or destructive runtime behavior.

Install only if you want an agent to keep local long-term memory in your workspace. Treat the memory files as private notes: do not store passwords, API keys, tokens, raw private conversations, personal data, or sensitive internal procedures, and review PATH or deletion commands before running them.

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
93% confidence
Finding
The guidance explicitly tells the agent to persistently record interactions, outcomes, and especially the HOW/steps taken, but it provides no guardrails about excluding secrets, personal data, tokens, credentials, or other sensitive operational details. In practice, this creates a durable sink for sensitive information that may be exposed later through workspace access, prompts that read memory files, or accidental reuse.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The procedural-memory section encourages documenting technical integrations and recovery procedures, which commonly include endpoints, commands, account details, environment specifics, and troubleshooting artifacts. Without restrictions, this can lead to long-lived storage of secrets or sensitive infrastructure knowledge that increases the blast radius of any later prompt injection, file disclosure, or unauthorized workspace access.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.