ClawHub
Back to skill

Security audit

精英长期记忆免费版

Security checks across malware telemetry and agentic risk

Overview

This is a local long-term memory skill whose persistence behavior is disclosed and aligned with its stated purpose, though users should manage what gets saved.

Install this only if you want the agent to keep local memory files across sessions. Review SESSION-STATE.md, MEMORY.md, and the memory/ directory periodically, delete stale or sensitive entries, and do not let credentials, private personal data, or confidential material be stored there unless you explicitly intend that local retention.

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 (3)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill repeatedly instructs the agent to persist user preferences, decisions, and conversation context to local files across sessions, but it does not present a prominent user-facing consent, retention, or privacy warning. This creates a real privacy and data-governance risk because sensitive personal or project information may be stored indefinitely without clear notice or controls.

Ssd 3

Medium
Confidence
98% confidence
Finding
The skill explicitly directs the agent to persist user-provided details and preferences across sessions in local memory files. In the context of an AI agent skill, this is security-relevant because it can accumulate sensitive behavioral, personal, or project data and make it available to later sessions without strong boundaries, consent, minimization, or deletion controls.

Ssd 3

Medium
Confidence
98% confidence
Finding
The example operationalizes long-term retention and automatic reuse of a user's prior preference, demonstrating cross-session persistence as an intended feature. Without consent, scoping, and filtering, this behavior can propagate stale or sensitive information into future interactions and increase privacy exposure or prompt-injection persistence risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.