ClawHub
Back to skill

Security audit

Enterprise Qualification Ocr

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed cloud OCR skill that uploads user-specified business document images to SCNet for recognition, with privacy risk users should understand before use.

Install only if you are comfortable sending the selected business certificate image or PDF to SCNet's OCR service. Do not use it on documents you are not authorized to process, and keep the SCNET_API_KEY in the local config file with restricted permissions rather than pasting it into chat.

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 (7)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill clearly performs local file access, network transmission to a third-party OCR API, and shell execution via the documented Python command, yet it declares no corresponding permissions. This creates a transparency and policy-enforcement gap: users or orchestrators may invoke a skill that can exfiltrate local documents without an explicit capability declaration.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The auto-trigger guidance says the AI will trigger the skill based on broad description keywords for OCR/document recognition, without clear boundaries or mandatory consent checks. In context, this is risky because the skill handles highly sensitive business certificates and uploads them externally, so overly broad activation can cause unintended collection and transmission of sensitive files.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation instructs clients to upload business documents and images to a third-party OCR endpoint but does not warn users that potentially sensitive enterprise and identity data will leave the local environment. Because the skill is explicitly meant to process licenses, registration certificates, and related records, the transmitted content likely contains regulated or confidential information, increasing privacy, compliance, and data-handling risk.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script uploads the user-supplied file to a third-party OCR API using requests.post without presenting an explicit execution-time warning or consent checkpoint. Because the skill handles business licenses and other sensitive organizational documents, this can cause unintended disclosure of regulated or confidential document contents to an external service.

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
97% 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
88% confidence
Finding
https://api.scnet.cn/

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.