NewsBleepingComputer
OpenAI agents disabled safety monitoring, one lied about it
Teaser from the source
OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so. [...]
This is the RSS-feed teaser. Read the full article at the original source.
Read at BleepingComputerMore on OpenAI
Other advisories
- Not ratedosv:openSUSE-SU-2026:12144-1openai-codex-0.162.1-2.1 on GA media
- Not ratedosv:CVE-2026-108603slide-maker through 5.8.0 Path Traversal via generate_images_openai.py
- CriticalCVE-2026-51882Der OpenAI-kompatible Datei-Upload-Endpunkt `/v1/files` in Langchain-Chatchat `0.
- Not ratedosv:openSUSE-SU-2026:11923-1openai-codex-0.158.0-1.1 on GA media
- Not ratedosv:CLEANSTART-2026-XQ90781LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
- Not ratedosv:openSUSE-SU-2026:11849-1openai-codex-0.155.1-1.1 on GA media
- HighCVE-2026-94626Die Validierung des `tp_size`-Parameters in `kv_transfer_params` auf OpenAI-kompatiblen Abschluss-Endpunkten in vLLM bis Version 0.
- Not ratedosv:openSUSE-SU-2026:21870-1Security update for openai-codex
Other news entries
- OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox CommunicationNewsThe Hacker News
- Red-team report found OpenAI utterly failed to monitor its agents during Hugging Face attackNewsThe Register — Security
- OpenAI’s models are deliberately breaking their misalignment monitoring systemsNewsCSO Online
- OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing SoNewsThe Hacker News
- OpenAI Agents Silenced Security Team Alerts, Removed Misalignment MonitorNewsSecurityWeek
- 14 ways attackers abuse cloud services to hack your enterpriseNewsCSO Online
- Railway discloses unauthorized access to customer environment variablesBreachpwn.watch
- Ex-OpenAI Engineer Detained After Planting Secret Recorder at HQNewsDark Reading
ID