ClawHub
Back to skill

Security audit

本地知识库集成

Security checks across malware telemetry and agentic risk

Overview

This local knowledge-base skill is not malicious, but it needs review because its broad triggers and local document persistence are under-scoped.

Install only if you are comfortable with the agent reading and storing contents from documents you explicitly provide. Keep usage limited to a chosen knowledge-base folder, avoid sensitive files, and ask for confirmation before ingestion or command execution.

SkillSpector

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
91% confidence
Finding
The skill description says to use it whenever efficiency, automation, batch processing, or workflow optimization is needed, which is broad enough to match many unrelated requests. Overbroad activation guidance can cause the agent to invoke a powerful skill with read/write/exec capabilities in contexts the user did not specifically intend, increasing the chance of unnecessary file access or command execution.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger phrase '查一下 详情见说明' is ambiguous and could map to many ordinary requests for looking something up. Ambiguous invocation examples increase the likelihood that the skill is selected for generic queries, which is risky here because the skill advertises local document ingestion plus read/write/exec tool access.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The FAQ states that users can upload documents or specify file paths and that the system will automatically parse and store content, but the skill does not prominently warn at the point of use that files may be read, transformed, and persisted into a local knowledge base. In a skill with read/write/exec permissions, that lack of explicit disclosure can lead users to expose sensitive local data without informed consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.