ClawHub
Back to skill

Security audit

Agentmemory Hooks

Security checks across malware telemetry and agentic risk

Overview

This skill transparently describes automatic agent-memory capture, but users should understand that prompts and tool activity may be recorded by default.

Before installing, confirm you are comfortable with automatic memory capture of prompts, tool-use activity, session boundaries, and commit context. Avoid using it with secrets or regulated data unless you have reviewed the plugin configuration, storage location, retention behavior, and any options for limiting or disabling capture.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly states that prompts, tool use, and session boundaries are captured automatically, but it does not provide a prominent privacy warning about what data may be recorded or the sensitivity of that information. In a memory plugin context, this can lead users to unintentionally persist secrets, personal data, proprietary code, or other sensitive session content to a local or connected service without informed consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.