ClawHub
Back to skill

Security audit

Table Ocr

Security checks across malware telemetry and agentic risk

Overview

This OCR skill does what it claims, but users should understand that selected documents are uploaded to Scnet's external OCR API.

Install only if you are comfortable sending the specific images, PDFs, or archives you choose to Scnet's OCR service. Avoid submitting confidential, regulated, or proprietary documents unless your organization approves that service and endpoint.

SkillSpector

By NVIDIA
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 (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding
The skill documentation indicates capabilities to read local files, invoke Python from the shell, and send data over the network, but it does not declare permissions or boundaries for those actions. In this skill’s context, that matters because user-supplied local files are sent to an external OCR API, so the absence of explicit permission disclosure can lead to unintended data exfiltration or overbroad execution by the agent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The document describes uploading images/PDFs/archives and receiving OCR-extracted content from a third-party endpoint, but it does not clearly warn that user files and their contents are transmitted off-platform to an external service. In a table OCR skill, inputs commonly contain sensitive business records, IDs, invoices, or academic data, so the lack of disclosure can lead to unintended data exfiltration and privacy/compliance issues.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script uploads an arbitrary user-supplied local file to a third-party OCR endpoint, which creates a real data exfiltration/privacy risk if users process sensitive documents. While the network call is expected for an OCR skill, the code does not provide an explicit runtime warning, confirmation, allowlist, or redaction control before transmission.

External Transmission

Medium
Category
Data Exfiltration
Content
| 变量名 | 默认值 | 说明 |
|--------|--------|------|
| SCNET_API_KEY | 必需 | Scnet API 密钥 |
| SCNET_API_BASE | https://api.scnet.cn/api/llm/v1 | API 基础地址（一般无需修改） |

### 输出
Confidence
88% confidence
Finding
https://api.scnet.cn/

External Transmission

Medium
Category
Data Exfiltration
Content
# Sugon-Scnet OCR API 文档摘要

## 接口地址
`POST https://api.scnet.cn/api/llm/v1/ocr/recognize`

## 请求头
- `Content-Type: multipart/form-data`
Confidence
91% confidence
Finding
https://api.scnet.cn/

External Transmission

Medium
Category
Data Exfiltration
Content
)
        sys.exit(error_msg)

    config.setdefault('SCNET_API_BASE', 'https://api.scnet.cn/api/llm/v1')
    return config

def recognize_with_retry(ocr_type, file_path, config, retry_count=0):
Confidence
91% confidence
Finding
https://api.scnet.cn/

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.