ClawHub
Back to skill

Security audit

HTML OCR

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward MinerU-based HTML OCR helper, with the main caution that selected HTML and embedded images may be processed by a third-party service.

Install this only if you trust MinerU and the mineru-open-api CLI. Use a revocable MinerU token, avoid exposing the token in prompts or logs, and do not OCR confidential, regulated, or proprietary HTML unless MinerU's data handling is acceptable for that content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs users to authenticate with a token-backed third-party OCR service but does not disclose that HTML content may be sent off-host to MinerU/OpenDataLab systems for processing. This can cause accidental exfiltration of sensitive page contents, embedded data, or internal documents when users assume the skill operates purely locally.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.