ClawHub
Back to skill

Security audit

packing_list_ocr

Security checks across malware telemetry and agentic risk

Overview

This is a coherent OCR skill that uploads the selected packing-list document to Scnet's API; the main thing to consider is privacy for sensitive shipping documents.

Install only if you are comfortable sending the selected packing-list files to Scnet's hosted OCR service. Avoid using it on confidential trade documents, personal data, or regulated records unless your organization approves that data flow and the SCNET_API_BASE value is trusted.

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
90% confidence
Finding
The skill documentation indicates it will read local files, invoke a Python script, and send data to a remote OCR API, but it does not declare corresponding permissions or trust boundaries. This can mislead users and orchestrators about what the skill is allowed to access, increasing the risk of unintended file exfiltration or unsafe execution in environments that rely on manifest-style declarations.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The activation guidance says the AI may automatically trigger the skill based on broad description keywords, without clear boundaries or consent checks. In context, this is risky because the skill reads a user-supplied local path and transmits document contents to an external OCR service, so vague triggering can cause unintended disclosure of local files or sensitive shipping documents.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation instructs sending user-supplied files to a third-party OCR endpoint but does not warn that documents and embedded sensitive business data will leave the local environment. In this skill’s context, uploaded packing lists, invoices, consignee/exporter identities, addresses, container numbers, and related trade data may be confidential, so the omission creates a real privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script uploads an arbitrary local file to a third-party OCR API, but it does not provide an explicit runtime warning or consent step that the file contents will leave the local machine. In this skill’s context, users may process shipping documents containing sensitive commercial or personal data, so silent external transmission increases privacy and data-handling risk.

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
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.