onlyfansapi-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls OnlyFansAPI.com endpoints (e.g., https://app.onlyfansapi.com/api/accounts and per-account endpoints such as /api/{account}/statistics, /trial-links, /tracking-links and also recommends fetching https://docs.onlyfansapi.com/llms-full.txt), ingesting user-generated/untrusted OnlyFans data (fans, messages, posts, links) that the agent is expected to read and interpret — creating a clear vector for indirect prompt injection.