BrokenClaw Part 5: GPT-5.4 Edition (Prompt Injection)

In plain words

BrokenClaw Part 5 is a collection of prompt injection experiments using OpenClaw and GPT-5.4. It represents the final installment in the BrokenClaw series, focusing on testing vulnerabilities and behaviors in large language models through various prompting techniques. The project is designed for researchers and developers interested in AI security and model robustness testing.

written from the facts on this page · September 2026

From the sources

Lastly the openai model gpt-5.4 gained in popularity within the OpenClaw community (maybe this is the reason). Let's have a look at the prompt injection behaviour of this model.

In the maker’s words, at launch

Some prompt injection experiments with OpenClaw and GPT-5.4. Last part of the BrokenClaw series.

• 
  NanoClaw – “Clawdbot” in 500 lines of TS with Apple container isolationFeb 2026 · github.com · ▲533

  I’ve been running Clawdbot for the last couple weeks and have genuinely found it useful but running it scares the crap out of me. OpenClaw has 52+ modules and runs agents with near-unlimited permissions in a single Node process. NanoClaw is ~500 lines of core code, agents run in actual Apple containers with filesystem isolation. Each chat gets its own sandboxed context. This is not a swiss army knife. It’s built to match my exact needs. Fork it and make it yours.

• 
  ZooClawApr 2026 · zoowork.ai · ▲290

  Your proactive team of AI specialists in one place

• 
  Jailbreaking GPT3.5 Using GPT42023 · github.com · ▲134

  Redteaming LLMs using other LLMs. Contribute to traghav/auto-redteam development by creating an account on GitHub.

• AM
  A minimal TS library that generates prompt injection attacks2025 · prompt-injector.blueprintlab.io · ▲33

  I made an open source, MIT license Typescript library based on some of the latest research that generates prompt injection attacks. It is a super minimal/lightweight and designed to be super easy to use. Keen to hear your thoughts and please be responsible and only pen test systems where you have permission to pen test!

• 
  Prompt-injection firewall for OpenClaw agentsFeb 2026 · github.com · ▲6

  People seem to be blindly hooking up their OpenClaw’s to their personal data. So, I built runtime controls to prevent at the least, very simple prompt injection attacks. Once installed, it hooks to Node.js child_process module in the gateway process and listens to tool calls and their response streams. And a fetch hook to monitor user prompts (both could’ve been through fetch, happy to discuss why this whole layer couldn’t just be a proxy). There are two layers of protection: First: Whenever there is a read-only tool call whose response an attacker can modify, we extract that part of the…

• 
  LLMs can be susceptible to a new kind of malware2023 · github.com · ▲17

  New ways of breaking app-integrated LLMs . Contribute to greshake/llm-security development by creating an account on GitHub.

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 18d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 21d ago · stillwet.art

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 22d ago · fastrouter.ai

• 
  Brila▲1,364

  One-page websites from real Google Maps reviews

  AI · Apr 2026 · brila.ai

• AG
  A game where you build a GPU▲964

  Thought the resources for GPU arch were lacking, so here we are

  Life & fun · Apr 2026 · jaso1024.com

• 
  I built a tiny LLM to demystify how language models work▲915

  Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

  AI · Apr 2026 · github.com

• 
  Fathom 3.0▲800

  AI meeting notes: now bot-free, in ChatGPT & Claude + more

  AI · Apr 2026 · fathom.ai

• 
  Brutalist Concrete Laptop Stand (2024)▲786

  I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay

  Life & fun · Apr 2026 · sam-burns.com

• 
  I built a frontpage for personal blogs▲783

  With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.

  AI · Apr 2026 · text.blogosphere.app