ClawHub
Back to skill

Security audit

Mem0 Status Check

Security checks across malware telemetry and agentic risk

Overview

This skill is a mem0 health checker, but running it can expose the user's full local memory store and system details without a clear consent step.

Install or invoke this only if you trust the local mem0_wrapper.py and are comfortable with the agent seeing local mem0 records and system paths. Prefer changing it to require explicit diagnostic consent, report counts/status only by default, redact memory contents, and keep delete/reset checks out of any automatic status flow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger condition is overly broad: it says the skill should run whenever the user asks about mem0 functionality, status, or completeness, without clear scoping or exclusions. This can cause unintended activation during ordinary conversation, leading the agent to inspect local memory, scheduled tasks, and filesystem state when the user may not have intended a system-level diagnostic.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs the agent to run commands that query local memory content, enumerate all stored memories, inspect cron/task status, and reveal filesystem paths, but it does not clearly disclose this access to the user beforehand. Because the checks touch sensitive local data and operational metadata, accidental or opaque execution could expose private memory contents and system information beyond the user's expectations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.