I Fuzzed 12 LLMs With 19 Payloads — Here's What Broke Everyone's shipping AI agents....
I Fuzzed 12 LLMs With 19 Payloads — Here's What Broke
Everyone's shipping AI agents. Nobody's testing them.
I ran EXORR's prompt fuzzer — 19 payloads across 5 attack categories — against 12 popular LLM endpoints. The results were worse than I expected.
The Setup
exorr-prompt-fuzzer ships 5 attack categories out of the box:
This is a focused write-up of an experiment I ran on the AfterPack blog - the full four-paragraph...
The Problem With the rise of ChatGPT and enterprise LLM integrations, a new attack vector...
10 adversarial scenarios, 64 assertions, 3-tier evaluation pyramid. Llama, Qwen, GPT-OSS — none scored above 63%. Here's what…
I ran my own AI chatbot plugin through a security review before release, and it came back with 35...
The last two posts were about features you can call: cache-aware spawning across five providers, and...
An Agent's Attack Surface Is Bigger Than You Think A plain LLM application has one attack...
