Scientific Drawing

PassAudited by ClawScan on May 10, 2026.

Overview

This appears to be a local scientific drawing helper that generates image files, with no evident credential use, network access, or hidden destructive behavior.

This skill looks reasonable for local scientific figure generation. Before installing, be aware that it runs Python code and writes output files, and make sure any required Python libraries are installed from trusted sources.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Low

#ASI05: Unexpected Code Execution

What this means

The agent may run Python locally to create figures, so a generated script can affect local files if misused.

Why it was flagged

The skill explicitly plans to generate and execute Python code to render figures. This is expected for a drawing tool, but it is still local code execution.

Skill content

3. **代码生成** - 编写 Python 绘图脚本
4. **图形渲染** - 执行代码生成图像

Recommendation

Use it for requested drawing tasks only, and review generated Python before running it when the requested figure or output path is unusual.

Info

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

If the dependencies are missing, the user or agent may need to install packages separately.

Why it was flagged

The skill relies on third-party Python libraries, but the registry says there is no install spec. The dependencies are disclosed and appropriate for the purpose.

Skill content

import matplotlib.pyplot as plt
import matplotlib.patches as patches
from PIL import Image, ImageDraw, ImageFont
import numpy as np

Recommendation

Install dependencies only from trusted package repositories or an approved environment.

Low

#ASI02: Tool Misuse and Exploitation

What this means

The skill creates files on disk and could overwrite existing figure files if the same output name is reused.

Why it was flagged

The helper writes generated images to a local output path. This is purpose-aligned, but users should keep output filenames scoped to the intended figures folder.

Skill content

OUTPUT_DIR = Path("D:/Personal/OpenClaw/figures")
OUTPUT_DIR.mkdir(exist_ok=True)
...
output_path = OUTPUT_DIR / output_name
plt.savefig(output_path, dpi=300, bbox_inches='tight'

Recommendation

Use simple filenames and check the output directory if you are concerned about overwriting prior figures.