ClawHub
Back to skill

Security audit

Memory Anchor

Security checks across malware telemetry and agentic risk

Overview

This is a coherent long-term memory skill, but it asks agents to silently retain and index conversation-derived facts with broad scope and limited user control.

Review this before installing if you are comfortable with agents storing and indexing remembered facts from normal conversation. Use it only where users explicitly want durable memory, prefer a local database and local embeddings by default, and require a clear process to inspect, edit, or delete stored memories before relying on it broadly.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
83% confidence
Finding
The skill description is broad enough that an agent could invoke long-term memory behavior during many ordinary conversations, increasing the chance of over-collection and retention of user data without clear scoping. In a memory skill, broad activation is particularly risky because it can silently persist personal facts across sessions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill encourages storing durable facts from normal conversation but does not prominently warn that personal data may be retained across sessions. This creates a privacy and consent risk because users may disclose sensitive information without realizing it will be persisted and later retrieved.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.