Is kai-tw/kai-tw-figma safe?

https://github.com/openclaw/skills/tree/main/skills/kai-tw/kai-tw-figma

95
SAFE

This skill provides legitimate functionality for interacting with Figma's official API to read design files, export assets, and retrieve comments. The main security considerations are the requirement for a sensitive API token and the downloading of content from Figma servers, but these are necessary for the intended functionality.

Category Scores

Prompt Injection 100/100 · 30%
Data Exfiltration 95/100 · 25%
Code Execution 85/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 80/100 · 5%

Findings (4)

MEDIUM Requires sensitive FIGMA_TOKEN environment variable -5 ▶

The skill requires a Figma Personal Access Token which is a sensitive credential that grants access to user's Figma files and data. While necessary for functionality, this token should be treated as a password.

LOW Downloads content from external URLs -10 ▶

The skill downloads image files from URLs returned by the Figma API. While these URLs come from Figma's official servers, this represents a potential vector if the API responses were compromised.

LOW Executable Python code included -5 ▶

The skill contains executable Python code that makes network requests and writes files. Code appears legitimate and uses only standard library modules.

INFO Writes files to working directory -20 ▶

When exporting images, the skill writes files to the current working directory with predictable names like 'figma_export_.'. This could lead to file clutter but is not a security risk.