ClawHub
Back to skill

Security audit

OCR 批量图片文字提取 + 关键词标注 + Word 导出

Security checks for vulnerabilities and agentic risk

Overview

This skill performs user-directed OCR and keyword formatting, with no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Install only if you are comfortable uploading or providing the images to your agent for OCR. Avoid using confidential, legal, medical, business, or personal documents unless you are authorized to process them, and choose explicit input and output paths when using the helper script.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill appears to require file read/write capabilities to process uploaded images and generate a Word document, but those permissions are not declared in the skill metadata. Undeclared capabilities create a transparency and review gap, making it harder for users and platform controls to understand what the skill can access and increasing the risk of unintended file access or data leakage.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly processes user-uploaded images and extracts text, which can include sensitive personal, academic, legal, or business information. Because the prompt provides no privacy warning, consent cue, or handling guidance, users may unknowingly submit confidential material, increasing the risk of inappropriate exposure or retention in downstream systems.

Static analysis

No suspicious patterns detected.