ClawHub
Back to skill

Security audit

Engram

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed local memory skill whose main risk is privacy from persistent stored conversations, not hidden or malicious behavior.

Install only if you want the agent to keep searchable local memory across sessions. Avoid storing secrets, credentials, regulated data, or confidential conversations unless you are comfortable with that information being recalled later or included in exports; review the npm dependency before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description is broadly scoped to common agent needs like recalling past decisions, storing facts, and maintaining context across sessions, which makes it likely to activate in many ordinary workflows. Over-broad activation increases the chance that sensitive user or task data will be routed into persistent memory without a narrowly defined need or an explicit privacy gate.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The instruction to pipe raw conversation text directly into persistent memory encourages bulk retention of potentially sensitive content without warning about privacy, minimization, consent, or retention limits. In an agent context, this can capture credentials, personal data, confidential business information, or safety-relevant context and preserve it beyond the current session.

Session Persistence

Medium
Category
Rogue Agent
Content
---
name: engram
description: "Persistent semantic memory for AI agents — local, fast, free. Use when agent needs to recall past decisions, store new facts/preferences, search conversation history, or maintain context across sessions."
metadata:
  openclaw:
    emoji: "🧠"
Confidence
94% confidence
Finding
maintain context across sessions

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.