scrapling-skill

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

• Third-party content exposure detected (high risk: 0.80). This skill's required workflow (SKILL.md) and the included scripts (scripts/diagnose_scrapling.py) explicitly run Scrapling against arbitrary public URLs—e.g., "scrapling extract get/fetch 'https://mp.weixin.qq.com/s/ARTICLE_ID?...'" and the smoke-test preview prints page content—which the agent must read and use to choose fetchers and next actions, exposing it to untrusted third-party content that could carry indirect prompt injection.