ClawHub
Back to skill

Security audit

Paper2diagram

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only paper-analysis skill that clearly discloses use of user-configured AI gateways, though users should avoid sending sensitive PDFs to gateways they do not trust.

Install only if you are comfortable sending the selected PDF or extracted paper content to your configured Gemini and Banana gateways. Review the separate workflow repository before running it, use a virtual environment or container, and avoid unpublished, proprietary, or regulated papers unless the gateway is trusted and approved for that data.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Transmission

Medium
Category
Data Exfiltration
Content
- **需要网络访问**：连接到你自己配置的 LLM / 图像网关（例如 dongli gateway）
- **环境变量**（可以在 OpenClaw 的 `skills.entries.paper2diagram.env` 中配置，也可以在 shell 中设置）：
  - `GEMINI_API_KEY`
  - `GEMINI_BASE_URL`（示例：`https://api.dongli.work/v1beta`）
  - `GEMINI_MODEL`（示例：`gemini-3-pro`）
  - `BANANA_PRO_API_KEY`
  - `BANANA_PRO_BASE_URL`（示例：`https://api.dongli.work`）
Confidence
88% confidence
Finding
The skill explicitly requires sending user-provided PDF contents to externally configured LLM and image-generation gateways, which can expose sensitive research documents or embedded personal data to third-party services. Although the documentation discloses this behavior and frames it as user-configured infrastructure, the external transmission remains a real confidentiality risk, especially for unpublished papers, proprietary datasets, or regulated content.

Static analysis

No suspicious patterns detected.