The Agent Skills Directory

[CREDENTIALS_UNSAFE]: A hardcoded Xiaohongshu session cookie (XHS_COOKIE) was found in the .env file. This exposes active session credentials and could allow unauthorized access to the associated account.
[EXTERNAL_DOWNLOADS]: The skill initiates the download and installation of the Chromium browser through Playwright (playwright install chromium and npx playwright install chromium). While Playwright is a well-known service from Microsoft, it involves executing external binaries.
[COMMAND_EXECUTION]: The skill workflow involves executing multiple Python and Node.js scripts (render_xhs.py, publish_xhs.py, render_xhs_v2.js) to process content, render images using a headless browser, and publish data to the Xiaohongshu platform.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted user data to generate Markdown content for rendering and publishing.
Ingestion points: User-provided descriptions and source materials in SKILL.md (Step 1).
Boundary markers: None identified; the skill does not use delimiters to isolate user input from its own instructions.
Capability inventory: Subprocess execution via Playwright, file system writes for generated images, and network operations to Xiaohongshu APIs in publish_xhs.py and comment_manager.py.
Sanitization: No evidence of sanitization or escaping was found in the scripts that interpolate content into HTML templates.

xhs-note-creator