Security audit

Memory Setup

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-built for persistent memory search, but it under-explains sensitive local indexing and possible third-party embedding exposure.

Review exactly which files and sessions this skill indexes before installing. Prefer a local embedding provider for sensitive work, exclude secrets and private transcripts, and avoid shared or organizational content unless everyone affected has approved the indexing and retention model.

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: 95% confidence
Finding: The skill explicitly encourages enabling persistent memory over MEMORY.md, daily logs, sessions, and user preferences, but it provides no privacy, retention, consent, or sensitivity guidance. This can lead users to index personal data and past transcripts without understanding that sensitive information may be stored, surfaced later, or exposed through search results.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The provider setup instructs users to configure Voyage or OpenAI API keys but does not warn that embedding requests may send memory content, logs, or transcripts to third-party services. Because this skill is specifically about indexing persistent context, the omitted disclosure is more dangerous: users may unknowingly transmit sensitive historical data outside their environment.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.