scrapling

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

• Third-party content exposure detected (high risk: 0.90). The skill (SKILL.md and scripts/scrapling_scrape.py) directly exposes the agent to arbitrary public web pages via fetchers, spiders, CLI, and MCP tools (get/fetch/stealthy_fetch) that retrieve and parse untrusted third-party content (open URLs) which the agent is expected to read and use to drive follow-up actions such as extraction and pagination.