Security audit

Memory Enhancer Pro

Security checks across malware telemetry and agentic risk

Overview

This memory-management skill appears local and not malicious, but it should be reviewed because it reads sensitive OpenClaw memory/profile files and has confusing paths that can write outside the Pro skill folder.

Install only if you are comfortable with local scripts reading your OpenClaw memory, session, user, soul, and agent files. Before enabling schedules or running cleanup, verify the install path, fix the hardcoded skills/memory-enhancer references if this is installed as memory-enhancer-pro, and back up memory files before using --execute.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill documentation advertises file reads, file writes, deletion, and shell-based execution examples, yet no explicit permissions are declared. This creates a transparency and consent problem: users or hosting systems may invoke a skill with broader capabilities than expected, especially because it accesses workspace memory, config, logs, and cleanup paths.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The skill materially overstates its behavior and understates destructive effects. It claims semantic/intelligent processing and compression, but the analyzed behavior includes deletion of old memory files and weaker implementations than advertised; this can mislead users into trusting automation that may remove data or process sensitive memory inaccurately.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal