ClawHub
Back to skill

Security audit

PLUR Memory

Security checks across malware telemetry and agentic risk

Overview

This appears to be a memory/sync skill whose persistence behavior is central to its purpose, but users should treat stored memories as sensitive because they may be reused later and shared across tools or devices.

Install only if you want an agent memory layer that can persist context and reuse it later. Do not store credentials, tokens, private personal data, or confidential business details unless you understand where memories are stored, how sync works, and how to review or delete them.

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 (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly describes permanent cross-session storage and automatic reinjection of prior data, but it does not provide a clear warning about retention duration, sensitivity of stored content, or the privacy/security implications of later reuse. This creates a real risk that users or downstream agents will persist secrets, personal data, or sensitive operational details without informed consent or appropriate handling expectations.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The shared-memory and sync sections state that memory is shared across tools and can propagate across devices, but they omit a clear warning that any stored information may spread beyond the original context. This materially increases exposure risk because a mistaken or sensitive memory can be replicated to multiple agents, applications, and systems, amplifying confidentiality and integrity impacts.

VirusTotal

41/41 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.