Security audit

Unified Memory V5

Security checks across malware telemetry and agentic risk

Overview

This looks like a real memory skill, but it needs Review because it can automatically record and reuse conversations while the submitted install package is incomplete and its access scope is broader than disclosed.

Review before installing. Use it only if you want an automatic long-term memory system that may record conversations, index them, and inject recalled content into future prompts. Verify the real install source, keep cloud/provider credentials disabled unless intended, and confirm you can inspect, delete, export, and stop stored memories.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access, suspicious.exposed_secret_literal (+1 more)

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: merged-src.js:16446

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: merged-src.js:19

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: merged-docs.md:6106

Sensitive-looking file read is paired with a network send.

Warn

Code: suspicious.potential_exfiltration
Location: merged-src.js:89862