ClawHub
Back to skill

Security audit

trademark_certificate_ocr

Security checks across malware telemetry and agentic risk

Overview

This skill uploads a user-specified trademark certificate file to Scnet's OCR API, which matches its stated purpose but requires privacy awareness.

Install only if you are comfortable sending trademark certificate images or PDFs to Scnet for OCR. Keep the API key in config/.env with restrictive permissions, avoid using the skill on unrelated sensitive documents, and verify SCNET_API_BASE before processing confidential files.

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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation indicates capabilities to read local files, access the network, and invoke shell commands, but it does not declare any corresponding permissions or trust boundaries. This is dangerous because users and orchestration systems cannot accurately assess what the skill will access, increasing the chance of unexpected file exposure or outbound data transmission during OCR processing.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description only says the skill supports OCR for trademark registration certificates, but does not clearly define invocation boundaries, acceptable document types, or misuse constraints. In agentic systems, vague descriptions can cause over-broad routing and accidental invocation on unrelated sensitive documents, increasing the risk of inappropriate data exposure or incorrect automation.

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

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.