NEAR AI discloses breach: SGLang RCE flaw let attacker reach infra, ~100 users' data exposed
bingxu_ · x · 2026-11-11
NEAR AI published an incident report: on November 8 an attacker exploited a remote code execution vulnerability in SGLang, the open-source inference engine running its servers, gained code execution on one inference server, and pivoted into part of the company's infrastructure.
What was accessed:
- Account details (email, name, and for some accounts plan and balance info) for 100 users, via an internal system behind a deprecated Private Chat deployment
- Chat history, settings and logs of 18 agents on a legacy deployment not running in NEAR AI's confidential computing (TEE) environment
- API keys of two Cloud customers exposed in logs; keys have been revoked
- On Nov 8, user requests processed on the compromised server, including confidential-mode requests, could have been observed; no indication stored Private Chat conversations or uploaded files were accessed
NEAR AI revoked all sessions and admin credentials, replaced agent tokens, took Private Chat offline, and patched the SGLang vulnerability. Quoting author bingxu reacted skeptically.
More from Infra
- HF tokenizers v1.0.0-rc.4 restores Python APIs and encodes up to 17x faster — art_zucker · 2026-11-11
- MacPaw's Elix claims fastest LLM inference on Apple silicon, winning all 33 benchmarks — JosephJacks_ · 2026-11-11
- Which tasks have you fully moved from cloud models to local ones? — FulcraDynamics · 2026-11-11
- X's recommender is multimodal: CLIP and MultimodalPostEmbedderV5 embeddings feed Phoenix retrieval — cocktailpeanut · 2026-11-11
- Bittensor launches Gamma Tokens for native agent payments across subnets — markjeffrey · 2026-11-11
- Meta's Muse Spark Open, 816B params with 1M context, goes live on ai& inference — DavidBennett__ · 2026-11-11