Back to skill

Security audit

Super Taizi Knowledge Base

Security checks across malware telemetry and agentic risk

Overview

This is a simple personal knowledge-base skill that stores and searches user-provided content locally, with privacy cautions but no evidence of hidden exfiltration or destructive behavior.

Install only if you want user-provided notes, text, and selected files to be stored and searchable in local OpenClaw knowledge-base directories. Avoid saving sensitive material unless you know how to remove it later, and verify the referenced local vector_kb.py script exists and is trusted before using the command examples.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrase "记一笔" is broad and can easily appear in ordinary conversation, increasing the chance the skill activates unintentionally. Because this skill writes and indexes user data into persistent local stores, accidental activation could cause unintended retention of sensitive or private content.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents persistent storage locations for vector data, ontology data, and notes, but does not warn users that their content will be written to and retained in local directories. This creates a privacy and consent risk because users may provide sensitive information without realizing it will be indexed and stored beyond the immediate session.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill states that files are automatically indexed and searchable after being added, but it does not prominently warn that uploaded file contents will be stored and processed for retrieval. If users add sensitive documents, this can lead to unanticipated exposure through later searches or local access to indexed data.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.