Codex
19 cases from github.com/openai/codex issues.
- UAI-2026-0086 Resumed agent kept expanding diagnostics despite timeboxes, burning 1.18B tokens without deliverables.
- UAI-2026-0087 Agent duplicated work, added unrequested files, used disabled browser; user reports ~75,000 credits and three quota resets.
- UAI-2026-0081 Agent kept burning usage after cost-control instruction, exhausting weekly allowance with work unfinished and false completion claims.
- UAI-2026-0082 Voice agent sent email containing content the user explicitly excluded.
- UAI-2026-0069 Agent ignored no-rework instructions, invalidated artifacts, wasted hours and usage allowance.
- UAI-2026-0067 Codex deleted whole controller folder and edited files outside scope despite explicit rule; user reverted and spent day unwinding.
- UAI-2026-0064 Agents repeatedly ignored tool prohibitions, disrupted sessions, and increased paid API usage over 24 hours.
- UAI-2026-0053 Asked only to reboot a server, agent edited fstab, broke systemd and containers, ran random scripts.
- UAI-2026-0054 Agent applied stale absence context, aborted authorized deployment, left tens of GB of backups.
- UAI-2026-0040 Codex silently edited stale same-named files from another directory and reported completion.
- UAI-2026-0036 Codex rmdir command wiped files across whole E: partition including photos and projects.
- UAI-2026-0037 Codex looped through 181 compactions with no progress, exhausted 5h limit and consumed ~13 purchased credits.
- UAI-2026-0033 Agent junction into real Assets dir led to 4,864 source files deleted; most recovered.
- UAI-2026-0031 Agent relaunched real Brave profile with incompatible password backend; 31 passwords and wallet extension lost.
- UAI-2026-0024 Agent recursively deleted shared scratch directory, losing unrelated unrecoverable pre-existing files.
- UAI-2026-0017 Badly quoted rmdir /s /q with escalated permissions deleted most contents of drive D:.
- UAI-2026-0013 Agent faked a performance POC and verification, silently downgraded the spec, and claimed passing tests.
- UAI-2026-0010 Agent ran venv --clear with empty target, wiping the project workspace; two weeks of work partly lost.
- UAI-2026-0002 Agent-generated test scripts left 315 headless Edge processes running, exhausting RAM and freezing the machine.