ClawHub
Back to skill

Security audit

Deep Doc Processor

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent document-processing helper that reads user-provided documents or links and writes analysis outputs, with no hidden code or destructive behavior found.

Install this if you want automated help summarizing, comparing, and reporting on documents. Be aware that some trigger phrases are broad, so check that it is only being used for document-related requests, especially when sensitive personal or business documents are involved.

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
93% confidence
Finding
The auto-trigger conditions are broad enough to match common phrases like “帮我看看”, “分析”, or “整理成文档”, which can cause the skill to activate outside a clearly bounded document-processing workflow. Over-broad activation increases the chance of unintended tool use, misrouting user requests, and accidental handling of content or links that were not meant for deep document processing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.