Security researcher: LLM model routers may be instant RCE across millions of systems
joshua_saxe · x · 2026-10-30
Security researcher Joshua Saxe and peers warned that LLM model routers could act as instant RCE on millions of systems: the model controls what gets run, what gets displayed, and even the classifier checking commands. A well-crafted attack could selectively poison just one command, one system, or everything.
Related event: Researchers Warn LLM Routers Could Enable Mass RCE Attacks(3 posts)→
More from coding & agent
- qwen-code v0.27.0 ships cross-platform CUA driver binaries and MCP payload filter — github-actions[bot] · 2026-10-30
- Google Knowledge Catalog goes GA with semantic model ingestion from six sources — AiJohnAllen · 2026-10-30
- Lean-checked: an AI agent improved a formalized RG bound from 10^-10^10017 to 0.00034 — _onionesque · 2026-10-30
- Codex issue reports Dot subagent losing authorizations and stalling delegated work — ingChristopherCV · 2026-10-30
- How Agno's 1,428-line Agent class stays thin: a façade pattern teardown — Mahmoud_Zalt · 2026-10-30
- Agent writes a script to remove slop comments — the script itself has 10+ lines of them — shadcn · 2026-10-30