ClawHub
Back to skill

Security audit

Memory Management

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed workspace-memory maintenance guide, but users should be careful before enabling automatic cleanup or cron-based maintenance.

Install only if you want an agent to maintain persistent workspace memory. Before enabling cron or apply-mode batch runs, set MG_WORKSPACE to a narrow project directory, run dry-runs first, keep backups or snapshots, and confirm your retention/deletion policy for archived or retired memories.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly defines automated memory extraction, archiving, and cleanup operations over persistent files, but provides no warning, confirmation step, retention controls, or user consent mechanism before modifying stored data. In an agent setting, this can lead to unintended deletion, archival, or alteration of records that may be important for auditability, trading review, or recovery, making the skill materially risky even though it is framed as maintenance.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.