ClawHub
Back to skill

Security audit

Business License Ocr

Security checks across malware telemetry and agentic risk

Overview

This skill does upload user-selected business license files to SCNet's OCR API, but that behavior is central to the skill and is prominently disclosed.

Install only if you are comfortable sending business license images and extracted business identity data to SCNet's OCR service. Use it only for documents you are authorized to process, keep the API key in the local config file with restrictive permissions, and verify the configured SCNET_API_BASE before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill documentation indicates it can read local files, invoke Python/shell commands, and send data over the network, but it does not declare corresponding permissions or execution boundaries. This creates a transparency and policy-enforcement gap: users or an orchestrator may trigger sensitive file access and external transmission without an explicit permission model, increasing the chance of unintended data exposure.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The auto-trigger guidance says the AI will trigger the skill based on description keywords, but it does not define strict activation conditions, confirmation requirements, or exclusions. Because this skill reads user-supplied local paths and uploads sensitive business-license images to a third party, ambiguous triggering could cause accidental invocation and unintended exfiltration of sensitive documents.

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
93% confidence
Finding
The skill is designed to transmit uploaded business-license images and extracted data to an external host, api.scnet.cn. Even though the documentation openly warns about this behavior, it still represents real external transmission of highly sensitive corporate identity and registration data, so accidental or unauthorized use can lead to privacy, compliance, and business-fraud risks.

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
95% confidence
Finding
The documentation instructs the skill to send user-supplied business license files to an external third-party OCR endpoint at api.scnet.cn. Because business licenses contain sensitive corporate and personal data, this creates a real data exfiltration/privacy risk unless users are clearly informed, consent is obtained, and the third-party processor is vetted and contractually approved.

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
95% confidence
Finding
The skill transmits the provided document and an API bearer token to a third-party remote service at api.scnet.cn for OCR processing. This is an actual data-exposure risk because business licenses contain sensitive corporate and personal information, and the code does not provide consent checks, destination allowlisting beyond config, or minimization controls before external transmission.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.