ClawHub
Back to skill

Security audit

Tinmem Memory System

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate persistent-memory skill, but it automatically stores and reuses conversation information across sessions without clear consent, retention, or disable controls.

Install only if you want the assistant to keep long-term memory. Before using it, confirm how memories can be reviewed, deleted, disabled, scoped, and excluded; avoid sharing secrets, credentials, regulated data, or confidential work details unless you are comfortable with them being stored and reused later.

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
95% confidence
Finding
The skill explicitly states that memories are automatically extracted after each conversation turn, persisted across sessions, and injected back into future context, yet it provides no user-facing consent, retention limits, or privacy controls. This creates a real privacy and data-governance risk because sensitive user information may be stored and resurfaced without clear authorization or transparency, increasing the chance of over-collection, unintended disclosure, and cross-session leakage.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.