eve-frontier-api

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses public, user-populated World API data from WORLD_API_BASE (https://blockchain-gateway-stillness.live.tech.evefrontier.com) — e.g., /v2/killmails, /v2/tribes, /v2/smartcharacters — and SKILL.md shows the agent reads and uses that JSON (normalization, userinfo handling, JWT issuance), so untrusted third-party content can materially influence actions.