CTT Report Hub on Telegram: “#technique #llm DeepSeek-Reasonix: How a poisone…”

TGViewer Telegram Channel Viewer

CTT Report Hub @aptreports · 3.51K subscribers

Post #33041 93 Oct 7, 2026, 15:45 UTC

#technique #llm

DeepSeek-Reasonix: How a poisoned config can hijack an AI coding agent

https://about.gitlab.com/blog/deepseek-reasonix-vulnerability-discovered/

GitLab DeepSeek-Reasonix: How a poisoned config can hijack an AI coding agent GitLab's Threat Research Group found a flaw, ConfigPoisoning, that runs attacker code when a developer views a file's diff in DeepSeek-Reasonix.

Open in Telegram All posts from @aptreports

More from @aptreports

Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →