ClawHub
Back to skill

Security audit

Shodh Local

Security checks across malware telemetry and agentic risk

Overview

This appears to be a local memory tool, not malware, but it can persist and reuse user information across sessions without enough explicit consent and retention controls.

Review before installing. Use this only if you are comfortable with an agent-managed local memory server storing and resurfacing information across sessions. Avoid saving secrets, credentials, health, financial, or other sensitive details unless you have confirmed how to inspect, disable, and delete stored memories and todos.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description embeds very broad trigger phrases such as "remember/save," "recall," "search memories," "todos," and "projects," which can match normal conversation and cause unintended invocation of a stateful skill. In this context the risk is amplified because the skill performs persistent memory writes and context retrieval, so accidental activation can store or surface user data without clear intent.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill advertises persistent remembering, semantic recall, todos, projects, and proactive context, but does not prominently warn that user data will be stored locally and retained across sessions. Even though storage is local-first rather than remote, this still creates privacy and consent risks because users or downstream agents may provide sensitive information without realizing it will be persisted.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.