User claims Codex subagent prompt encryption can be bypassed by spawning subagents differently
Aryvyo · x · 2026-09-09
Responding to theo's finding that OpenAI Codex encrypts prompts sent to subagents, user Aryvyo claims he accidentally discovered a bypass: getting the model to spawn subagents via another route exposes the prompts — an unconfirmed hole in OpenAI's anti-distillation protection.
Related event: Users Find Way to Bypass Codex's Encrypted Subagent Prompts(2 posts)→
More from coding & agent
- A Personal AI Reading Workflow: Turning a 2-Hour Podcast Into a 10k-Word Note — jiayuan_jy · 2026-09-09
- Semantic Cache Verification Measured: 30-40ms on the Hot Path vs 1.7s for an LLM Judge — Reasonable_Royal_621 · 2026-09-09
- HyperFrames hits #1 on GitHub as Claude Code-made launch video clocks 3M views in 2 days — toolstelegraph · 2026-09-09
- AI assistants may need their own email addresses as users balk at full inbox access — _AustinCalvert_ · 2026-09-09
- Dimillian's dev tool adds worktree creation on any branch after user requests — Dimillian · 2026-09-09
- Dev built a custom procedural drawing engine via Astra — all Evergrow art is drawn in code — Dimillian · 2026-09-09