ClawHub
Back to skill

Security audit

enterprise_license_ocr

Security checks across malware telemetry and agentic risk

Overview

This skill uploads a user-selected enterprise license document to Scnet for OCR and I found no hidden persistence, destructive behavior, or unrelated data access.

Install this only if you are allowed to send the target license documents to Scnet's OCR service. These documents may contain company identifiers, addresses, legal representative names, license numbers, and bank account details, so confirm vendor approval and data-handling requirements 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 (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill documentation indicates capabilities to read local files, invoke shell commands, and send data over the network, but it does not declare any permissions or capability boundaries. This creates a transparency and consent gap: an agent may access sensitive local documents and transmit them externally without explicit permission signaling to the user or platform.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation guidance says the AI will auto-trigger the skill based on broad description keywords, with example prompts covering generic document-recognition requests. Overly broad triggers can cause unintended execution on sensitive local files, especially when combined with external transmission to an OCR API.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill handles local document images but does not clearly warn in the main description that those files are sent to an external OCR API. Because enterprise licenses and related documents can contain sensitive business identifiers and regulated information, silent transmission to a third party creates a material privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation explicitly instructs clients to upload enterprise license images, PDFs, and archives to a third-party OCR endpoint, but it does not warn that these files may contain highly sensitive business and personal data. The example responses include license numbers, social credit codes, names, addresses, and bank account information, which increases the risk of unintended external disclosure and unsafe downstream use.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description is overly broad and does not define when the skill should be invoked or what specific inputs it is intended to handle. In agent environments, vague activation scope can cause the skill to be selected for unintended documents or prompts, increasing the chance of unnecessary credential use, unintended data disclosure to the OCR backend, or misuse outside the enterprise-license context.

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
94% 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
92% 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
84% confidence
Finding
https://api.scnet.cn/

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.