overview

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs clients to discover and parse public Nostr relay events (e.g., server announcements kinds 11316/11317 in SKILL.md, references/ceps.md and references/protocol-spec.md) and to act on tags like support_encryption and advertised capabilities, so untrusted, user-posted relay content can directly influence protocol behavior and tool use.