http-outcalls

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

• Third-party content exposure detected (high risk: 1.00). This skill's backend outcall module (mo:caffeineai-http-outcalls/outcall) explicitly allows making HTTP GET/POST requests to arbitrary URLs and passes the HTTP response into the provided transform callback (shown in SKILL.md), so the agent will read and act on untrusted public web content that could contain injected instructions.