n2n-federation

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads remote peer-composed content at runtime via n2n_knowledge_query(peer_identity, collection_id, query), where a peer’s documents are processed and an agent-composed cited answer is returned to the caller for the user’s query.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill instructs generating and enabling systemd service unit files (writing/enabling units via scripts), which modifies the host's service configuration and can change system state (potentially requiring elevated privileges), so it risks compromising the machine.