/dev/posts/

Tool call execution through user prompt injection (CSRF) of the llama-server Web UI

Published:

A user prompt injection vulnerability (CSRF) in the llama-server (llama.cpp) Web UI (Reprompt-like) allows attackers to inject arbitrary user prompt with query parameter (?q=...), potentially leading to arbitrary shell command execution, data exfiltration, etc. (through tool calls).

Read more…

llama.cpp quickstart (part 2)

Published:

How to quickly use llama.cpp for LLM inference (part 2). This is a follow-up of a previous post on the same topic.

Read more…

llama.cpp quickstart

Published:

How to quickly use llama.cpp for LLM inference (no GPU needed).

Read more…

Page 1 of 1 | | | JSON Feed | Atom Feed | RSS Feed