mcporter

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

• Third-party content exposure detected (high risk: 0.75). The skill’s workflow includes runtime fetching/scraping of arbitrary external web content via commands like mcporter call ... url:https://... and mcporter call --stdio ... scrape url=https://..., which can ingest outsider-authored free text into the agent’s LLM context.