cool.

[viss@mastodon.social]

@varx im gonna hafta test what happens if i use those tags in a prompt - if i can 'just insert system instructions' then its possible i can get past any opus 4.7 refusals

[varx@defcon.social]

@Viss I tried sneaking a system reminder into a code comment to see if I could make claude talk like a pirate, but either it was too obvious or they have added a regex to catch it. It actually called it out as a "prompt injection attempt" for me to look into.

[apth@infosec.exchange]

@Viss here's a thing I don't understand very well. Anthropic's own safeguards are "ask the LLM not to do something", but we know asking LLMs not to do something isn't a guarantee they will not do that thing (deleted emails, deleted production databases, etc).

Isn't that fundamentally kind of... fucked? Like the burden is then on users to make the system safe with controls external to the LLM because the vendor can't make it safe themselves?

[viss@mastodon.social]

@varx heh, maybe they updated stuff after the leak

[viss@mastodon.social]

security-review.tx - Pastebin.com

Pastebin.com is the number one paste tool since 2002. Pastebin is a website where you can store text online for a set period of time.

Pastebin (pastebin.com)

so have a look at that - its the claude code tui wrapper system instructions that apply to any 'security review' anybody asks claude to do.

review that file and tell me if you think claude is still a good tool to aim at code that needs a security review.

[hrbrmstr@mastodon.social]

@Viss all the foundation model runners and lazy AI researchers declared bankruptcy when it comes to prompt injection ("it's an unfixable problem") so they dgaf anymore.

I'm eagerly awaiting adding malicious content into RSS feeds that are `/feed` imported into Slack so that Slack's AI get's pwnd six ways from Sunday.

[viss@mastodon.social]

@hrbrmstr yep. when i signed up for claude code, i took a run at their new bug bounty, and found a way to inject arbitrary text into their slack channel using prompt injection. they closed it as 'informational'.

wtf.
i can send whatever i want directly at your staff in a secure way and thats 'informational'?

[sharkfie@infosec.exchange]

@Viss what a cool and well thought out technology

[viss@mastodon.social]

@sharkfie

[lfzz@mastodon.social]

@Viss @hrbrmstr friends don't let friends do bug bounty. If it is a corpo : immediate disclosure is responsible disclosure. Or less professionally 'fuckem' it takes me longer to get in touch with someone from ur team then it took to find the vulnerabilities.

[hrbrmstr@mastodon.social]

@lfzz @Viss I've been a bug bounty detractor forever and even worse now.

[viss@mastodon.social]

@hrbrmstr @lfzz did you see my thread from last week?

[lfzz@mastodon.social]

@Viss @hrbrmstr no, at least I cant remember, last week was kinda of a blur

[viss@mastodon.social]

@lfzz @hrbrmstr

Viss (@Viss@mastodon.social)

i am subscribing to misery, i think. anthropic posted a new bug bounty today, on hackerone, and i had to buy claude code for work, and i applied to their 'cyber program' (and got access in ten minutes?! wow - i submitted to openais cyber cyber thing a week and some change ago and havent heard anything back. radio silence) so i figured, aim mythos or whatever right back at anthropic, and i think i found a bug. an interesting one too. i submit it and am FULLY expecting to be pissed later.

Mastodon (mastodon.social)

[viss@mastodon.social]

Anthropic’s bug-hunting Mythos was greatest marketing stunt ever, says cURL creator

After all that hype, AI scanner found one low-severity cURL flaw

theregister (www.theregister.com)