Security audit

NBJ OB1 Agent Memory for OpenClaw

Security checks across malware telemetry and agentic risk

Overview

The reviewed artifact appears purpose-aligned and the supplied scanners reported no malicious or suspicious findings.

Install only if you intend to grant the tool normal ClawHub package-management authority. Review commands that publish, delete, moderate, or print stored tokens before running them, and keep any ClawHub token protected.

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

62/62 vendors flagged this plugin as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: dist/index.js:19
Evidence: this.accessKey = [REDACTED];

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: src/client.ts:31
Evidence: this.accessKey = [REDACTED];