Security audit

Clawhub

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed memory-governance aid that stores or checks local memory files only when the host or user explicitly integrates it.

Install this only if you want your agent system to use explicit memory-routing rules. Before integrating it, decide which local files or adapter paths may receive memories, avoid storing secrets or sensitive personal data, and use the provided retention and checker guidance to keep short-term state from becoming permanent by accident.

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

Low

Confidence: 90% confidence
Finding: The skill explicitly describes writing memory outputs to local files or host-provided storage, but it does not clearly warn the user that generated content may be persisted outside the immediate interaction. This can lead to unintended retention of sensitive or private information, especially in a memory-related skill where users may assume outputs are ephemeral.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: This document explicitly routes different categories of information into persistent files and directories, including user preferences, project facts, proactive state, and working buffers, but it does not mention obtaining user consent, minimizing sensitive data, retention limits, or clearly warning that the information will be stored on disk. In a memory-governance skill, that omission is meaningful because the document operationalizes persistent storage behavior and could lead agents to save personal or sensitive data in multiple locations without the user's awareness.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution, suspicious.exposed_secret_literal

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scripts/check-memory-host.py:71

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scripts/review-learning-candidates.py:37

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: memory_governor/audit/reconciliation.py:39

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: scripts/check-memory-host.py:300