Skip to content
View L4XB's full-sized avatar
🏄‍♂️
catching a wave
🏄‍♂️
catching a wave

Highlights

  • Pro

Organizations

@SixSentences

Block or report L4XB

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
L4XB/README.md
Lukas Buck · L4XB. LLMs, agents and security. An agent sketch with tools, memory and an untrusted input.

Pinned Loading

  1. SixSentences/sixsentences SixSentences/sixsentences Public

    Open, self-hostable research workspace for evidence, data, interviews, analysis, and writing.

    TypeScript 1 2

  2. dont-fix-later-fix-now dont-fix-later-fix-now Public

    An empirical evaluation framework for integrating real-time security feedback into LLM-based Infrastructure-as-Code generation using the Model Context Protocol (MCP).

    TypeScript

  3. prompt-engineering-trumps-tool-selection prompt-engineering-trumps-tool-selection Public

    A 540-test empirical evaluation framework assessing the security of Infrastructure-as-Code generated by AI assistants (Copilot, Cursor, Windsurf).

    Python

  4. research-on-prompt-inection-attacks-bachelor-thesis research-on-prompt-inection-attacks-bachelor-thesis Public

    A multi-layered system for detecting prompt injection attacks in AI systems, utilizing a microservice architecture with machine learning and rule-based approaches.

    Python