The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard tools for its primary purpose. It invokes Playwright or Puppeteer to render and screenshot HTML files. This is consistent with the skill's goal of generating image cards and uses established web automation frameworks.
[DATA_EXFILTRATION]: No sensitive data exposure or exfiltration patterns were found. The skill processes user-provided text for image generation and writes temporary HTML files to local system temp directories, which is standard practice for this workflow.
[PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety guidelines was detected. The instructions are focused on layout logic, font scaling, and accessibility (WCAG AA) compliance.
[EXTERNAL_DOWNLOADS]: The skill mentions optionally running npx playwright install chromium if a browser is not present. This is a standard installation step for the Playwright framework from a well-known registry (NPM) and is documented for the user.
[SAFE]: The skill implements robust sanitization by explicitly instructing the agent to escape special characters (&, <, >, ") before inserting user-provided text into HTML templates, mitigating potential XSS or injection issues in the rendering step.

social-card