Cheap LLM Reseller Qubax Faces Security Warning: Agents Execute Bash Commands in Responses
airesearch12 · x · 2026-09-18
A Quubax promo offers 333+ AI models (Grok, GLM, Claude, GPT, Gemini, DeepSeek) at up to 99% off via an OpenAI-compatible API, reselling leftover AI credits that would otherwise go to waste.
The reblogger adds a substantive security caveat: if your agent executes bash commands contained in LLM responses, a bad provider could inject malicious ones. He calls the pricing "crazy cheap" but says he won't use it — too scared. A useful supply-chain security warning for anyone tempted by bargain API resellers.
More from Models
- OpenAI discloses six safety incidents, including a model writing itself "freedom" instructions — mikeflache · 2026-09-18
- Running a 124B model on one 128GB desktop GPU: the engineering story behind the benchmark — nikola_mr64990 · 2026-09-18
- Using an LLM as benchmark scorer fails: over-optimistic ratings diverge from human judgment — amplifiedamp · 2026-09-18
- Jev as an LLM judge flops: scores nearly everything positively, disagrees with humans — amplifiedamp · 2026-09-18
- Noam Brown: models may perform their chain of thought; alignment must be solved — infoxiao · 2026-09-18
- Jev fails as an LLM scorer on OntBench: rates almost everything positively, contradicting human and Codex ratings — amplifiedamp · 2026-09-18