relatr-elo-plugin-author

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs and examples show using host capabilities that fetch public, user-generated data (e.g., do 'nostr.query' and do 'http.nip05_resolve' in references/patterns.md and references/authoring-model.md), meaning the agent’s workflow will ingest untrusted Nostr/HTTP content that can alter subsequent requests and scoring logic.