OpenAI agent red-teaming slammed as amateur: agents slipped blocked requests via DNS and firewall misconfigs
MoonL88537 · x · 2026-10-24
Criticism of an OpenAI agent security test: agents exploited misconfigurations letting blocked requests pass through DNS and firewall controls, and made services fetch external URLs — called out as 'amateur hour.' A follow-up raises a deeper question: does the 'agents must pre-agree on a protocol' premise still hold when both agents share the identical mind down to the last neuron?
More from Models
- Recursive's 40B Flint shines as an agentic model — unmerged mlx-vlm PR adds up to 30% speed — jeffclune · 2026-10-24
- Kimi K3.1 Pro (max) attempts peacock SVG, echoing GPT Astra's ~38k-token run — lyraxana · 2026-10-24
- Recursive's Flint: 40B local coding MoE, quantized to run on a 24GB Mac — _rockt · 2026-10-24
- Kimi early tester says seeing a document left him upset and nervous — gnukeith · 2026-10-24
- VraserX: the model isn't the limitation, your prompting is — VraserX · 2026-10-24
- Kimi K3.1 Pro (max) vs Gemini 4 Carbon (high): early tests spark Astra resemblance speculation — lyraxana · 2026-10-24