mcporter

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly shows commands like "mcporter call https://api.example.com/mcp.fetch url:https://example.com" and "mcporter call --stdio ... scrape url=https://example.com", which fetch/scrape arbitrary public URLs and thus expose the agent to untrusted third-party web content that could carry indirect prompt-injection.