ClawHub
Back to skill

Security audit

Knowledge

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local knowledge-capture helper, with some cautions around automatic saving and cleanup.

Install only if you want an agent to maintain a local markdown knowledge base. Set KNOWLEDGE_DIR deliberately, avoid saving sensitive material without confirmation, and run tidy in audit mode before enabling any scheduled tidy --fix job.

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
89% confidence
Finding
The trigger section is very broad ('saving something worth re-finding later', 'summarizing external content', 'tracking sourced claims'), which can cause the agent to invoke this skill in many loosely related contexts. Over-broad invocation increases the chance of unintended file writes, persistence of sensitive data, and use of downstream maintenance commands without the user explicitly asking to store information.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill recommends automatic cleanup operations, including 'know tidy --fix' in heartbeats or nightly cron, without a clear warning that this command modifies files. In a file-based knowledge store, auto-fix behavior can rename, move, normalize, or remove content unexpectedly, creating integrity and availability risks and making accidental data loss more likely.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.