ClawHub
Back to skill

Security audit

本地文件检索（免费版）

Security checks across malware telemetry and agentic risk

Overview

The skill is a local file search helper, but it needs Review because it can broadly read and index local documents or code without clear scope or consent boundaries.

Install only if you are comfortable letting the agent read and index files in the working directory you choose. Use it from a dedicated folder, avoid directories containing secrets or sensitive business data, and confirm any indexing or exec-based setup steps before they run.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill’s examples and scope are broad enough to trigger on generic requests like searching local documents, code, or building a knowledge base without clearly limiting when it should be used. In an agent environment with read, glob, grep, and exec capabilities, this can cause over-activation and unintended scanning of sensitive local files or repositories beyond the user’s precise intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill describes local file retrieval, codebase search, and exec-enabled operation but does not warn users that indexing documents or scanning repositories may expose sensitive information, nor that exec-based steps can affect system integrity. This omission increases the likelihood that users or agents invoke powerful file and command capabilities without informed consent or appropriate safeguards.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.