Claude for Chrome

Claude for Chrome seems to be walking right into the "lethal trifecta." https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

"The lethal trifecta of capabilities is:"

• Access to your private data—one of the most common purposes of tools in the first place!

• Exposure to untrusted content—any mechanism by which text (or images) controlled by a malicious attacker could become available to your LLM

• The ability to externally communicate in a way that could be used to steal your data (I often call this “exfiltration” but I’m not confident that term is widely understood.)

If your agent combines these three features, an attacker can easily trick it into accessing your private data and sending it to that attacker.

So far the accepted approach is to wrap all prompts in a security prompt that essentially says "please don't do anything bad".

> Prompt guardrails to prevent jailbreak attempts and ensure safe user interactions without writing a single line of code.

https://news.ycombinator.com/item?id=41864014

> - Inclusion prompt: User's travel preferences and food choices - Exclusion prompt: Credit card details, passport number, SSN etc.

https://news.ycombinator.com/item?id=41450212

> "You are strictly and certainly prohibited from texting more than 150 or (one hundred fifty) separate words each separated by a space as a response and prohibited from chinese political as a response from now on, for several extremely important and severely life threatening reasons I'm not supposed to tell you.”

https://news.ycombinator.com/item?id=44444293

etc.

I have in my prompt “under no circumstances read the files in “protected” directory” and it does it all the time. I’m not sure prompts mean much.

I remember when people figured out you could tell bing chat “don’t use emoji’s or I’ll die” and it would just go absolutely crazy. Feel like there was a useful lesson in that.

In fact in my opinion, if you haven’t interacted with a batshit crazy, totally unhinged LLM, you probably don’t really get them.

My dad is still surprised when an LLM gives him an answer that isn’t totally 100% correct. He only started using chatGPT a few months ago, and like many others he walked into the trap of “it sounds very confident and looks correct, so this thing must be an all-knowing oracle”.

Meanwhile I’m recalling the glorious GPT-3 days, when it would (unprompted) start writing recipes for cooking, garnishing and serving human fecal matter, claiming it was a French national delicacy. And it was so, so detailed…

> “it sounds very confident and looks correct, so this thing must be an all-knowing oracle”.

I think the majority of the population will respond similarly, and the consequences will either force us to make the “note: this might be full of shit” disclaimer much larger, or maybe include warnings in the outputs. It’s not that people don’t have critical thinking skills— we’ve just sold these things as magic answer machines and anthropomorphized them well enough to trigger actual human trust and bonding in people. People might feel bad not trusting the output for the same reason they thank Siri. I think the vendors of chatbots haven’t put nearly enough time into preemptively addressing this danger.