ClawHub
Back to skill

Security audit

deep-doc-processor

Security checks across malware telemetry and agentic risk

Overview

This skill is a document summarization and analysis helper whose file, web, OCR, and report-writing behavior matches its stated purpose.

Before installing, understand that the skill may read user-provided documents and webpages and may use browser-based access for pages behind login walls. Use it only with files and links you intend the agent to analyze, especially for private or business-sensitive material.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The auto-trigger conditions include broad everyday phrases such as '帮我看看', '分析', and '整理成文档', which can cause the skill to activate in many unrelated conversations. This increases the chance of unintended file, URL, or webpage processing, expanding the attack surface and potentially causing unreviewed access to user-provided content or external resources.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.