ClawHub

Daily Memory Keeper

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is coherently focused on archiving agent memory, with disclosed persistence and cleanup behavior that users should configure carefully.

Before installing, confirm the archive directory, retention period, and auto-clean setting. Avoid storing secrets or highly sensitive information in agent memory, and review recalled memories before relying on them for important work.

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 (3)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The usage example includes the broad phrase “继续上次的工作” (“continue the previous work”), which overlaps with normal conversational intent and could invoke the skill unintentionally. In a memory-archiving skill, accidental activation is more dangerous because it can trigger retrieval or persistence of prior-session data without the user clearly consenting in that moment.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises periodic cleanup and configurable retention, but does not warn users that files may be automatically deleted based on age. This creates a real risk of silent data loss, especially for memory files that users may assume are preserved indefinitely as part of a knowledge base.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The description promotes automatic archiving and cross-session memory inheritance without any privacy notice about persistent storage, indexing, or later retrieval of prior conversation data. Because this skill handles potentially sensitive memory content across sessions, omission of a privacy warning increases the chance of over-collection, retention of sensitive data, and disclosure to later users or contexts.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal