feishu-doc-scraper

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill injects and runs scripts (scripts/feishu_dom_capture.js and the SKILL.md workflow) that read and interpret live Feishu document pages and SSR HTML (including image URLs from internal-api-drive-stream.* via scripts/download_feishu_images.py), using the page DOM/TOC/word counts to drive clicks, extraction, and follow-up actions—so it clearly consumes untrusted, user-generated third-party content at runtime which could carry indirect prompt-injection instructions.