ClawHub
Back to skill

Security audit

organization_code_certificate_ocr

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it sends a user-specified organization code certificate file to Scnet's OCR API and returns structured results.

Install only if you are comfortable sending the selected certificate image or PDF to Scnet's OCR service. Use files you are authorized to process, review Scnet's privacy and retention terms if the documents are sensitive, and keep SCNET_API_KEY out of chat logs and source control.

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
93% 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 execution boundaries. This creates a real transparency and consent problem because a user-provided local file may be transmitted to a third-party OCR API without an explicit permission model.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The automatic trigger guidance is broad enough that normal conversation about recognizing an organization code certificate could invoke the skill without clear user awareness of side effects. Because the skill reads a local path and sends the file to an external API, ambiguous activation boundaries increase the risk of unintended data disclosure.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation instructs users to upload document files to an external OCR endpoint but does not clearly disclose that potentially sensitive images, PDFs, and extracted text will be transmitted to and processed by a third-party service. In the context of organization code certificates, the uploaded materials can contain regulated business identity data, making the omission a meaningful privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script uploads a user-supplied file to a third-party OCR endpoint using requests.post, but there is no explicit runtime disclosure or confirmation at the point of transmission. In an agent/skill context, this can cause unintended exfiltration of potentially sensitive document contents because users may assume processing is local unless clearly warned.

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
90% 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
88% 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
86% confidence
Finding
https://api.scnet.cn/

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.