crawler

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

• Third-party content exposure detected (high risk: 0.90). This skill (SKILL.md and main.py) sends arbitrary public URLs to the Scout service (SCOUT_SERVICE_URL -> /v1/scout/inspect) via fetch_web_content and crawl_website, ingesting untrusted third-party web content (public sites) that the agent reads and which can materially influence subsequent actions.