Memory On Demand

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed, read-only memory search helper, but it may surface prior local history when broad history-related phrases are used.

Install this only if you want your agent to search prior QMD and OpenClaw memory when you ask history-related questions. Review what those memory sources contain, avoid storing secrets there, and ask the agent to confirm before searching if you want tighter control.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger terms are very broad, common conversational phrases like '之前', '以前', and '还记得吗', so the skill may activate during ordinary dialogue without clear user intent to search stored history. In this skill's context, that can cause unintended retrieval of memory/QMD data and expose prior session information or personal context that the user did not explicitly ask to access.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal