OpenAI has begun encrypting subagent prompts in its MultiAgentV2 system, removing the readable task audit trail and sparking concerns about accountability and security, according to a GitHub issue. Th…
OpenAI's Codex CLI tool now encrypts inter-agent messages in its MultiAgentV2 system, leaving the plain-text 'content' field empty and storing messages only in an encrypted field. A GitHub issue docum…
OpenAI's Codex tool now encrypts MultiAgentV2 message payloads end to end, preventing local audit trails from showing what parent agents asked child agents to do. The change, merged into main on 2026-…
A regression in OpenAI's Codex CLI encrypts MultiAgentV2 messages passed to subagents, removing human-readable task text from audit trails and making debugging difficult. The encryption change, merged…