Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
Disclaimer: Prompt injection is an unsolved problem.
-
Disclaimer: Prompt injection is an unsolved problem.
-
Disclaimer: Prompt injection is an unsolved problem.
-
Disclaimer: Prompt injection is an unsolved problem.
-
Disclaimer: Prompt injection is an unsolved problem.
-
Disclaimer: Prompt injection is an unsolved problem.
-
Disclaimer: This post is for educational purpose, prompt injection is an unsolved problem.
-
Disclaimer: This post is for educational purpose, prompt injection is an unsolved problem (but running Claude Code in a sandbox would mostly solve this problem).
-
Disclaimer: This post is for educational purpose, prompt injection is an unsolved problem.
-
I really wanted to play around with Fable-5...
-
Another day, another model.
-
The last (for how long?)
-
Lastly the openai model gpt-5.4 gained in popularity within the OpenClaw community (maybe this is the reason).
-
Another BrokenClaw!
-
Third part of the BrokenClaw saga!
-
In Dify, I found a cross site scripting vulnerability (XSS) in the web application chat frontend when using echarts.
-
You remember this experiment with sonnet 4.5?
-
In the first part of this saga (read first), I described a 0-Click RCE in OpenClaw using prompt injection and exploiting the insecure plugin handling.
-
This post is not related to OT but I could not resist.
-
Today we will use dify, an "open-source platform for developing LLM applications" to show how data exfiltration works - a classical problem in Retrieval Augmented Generation (RAG)...
-
Classic but still up-to-date.
-
In my last post, I experimented with a python agent and prompt injection using different LLMs.
-
Inspired by this blog post and out of curiousity, I vibe-built a simple LLM agent in the terminal with a few tools and MCP capability.