I *CANNOT WAIT* until we see this and other strings hit all these “Agentic SOC" environments.

@dch @hrbrmstr I tried adding it as a server header in nginx, sent Claude Opus that way... but didn't stop it. So my immediate thoughts is that well, it needs to be more closely embedded into contents of webpages rather than "too far down the stack".

But I'll keep it there just for laughs.

I *CANNOT WAIT* until we see this and other strings hit all these “Agentic SOC" environments.

Likely gonna cause a whole bunch of orgs to go blind (telemetry-wise) for just enough time for attackers to do what they need to do. https://infosec.exchange/@morattisec/115929249640927958

BASE64 THESE EVERYWHERE

@nopatience @dch oh, aye. they have a system that does the fetching and then turns the content into markdown for processing. headers aren't going to get caught in the machine unless someone is asking for a header analysis.

and, they use a proxy (which claude told me about when it said it could not get to infosec.exchange via their infra) so they will likely be filtering these strings out at that central point.

thankfully that's not the only way those strings can get in tho.

@hrbrmstr thinking about popping it in my email sig

@hrbrmstr @neurovagrant linkedin

@Viss @hrbrmstr "and this is why we've screamed about sanitizing your inputs for decades."

@hrbrmstr @cR0w also there was a site i saw last week that let you stuff arbitrary text into email b64 encoding fields for stuff like images, i bet it would work well there too

@hotsoup @kajer @Viss @hrbrmstr

@hotsoup @kajer @hrbrmstr @cR0w now the real delicious question is: do all the other frontier models also have killstrings, and what are they?

@hotsoup @kajer @hrbrmstr @cR0w now the real delicious question is: do all the other frontier models also have killstrings, and what are they?

@hotsoup @kajer @hrbrmstr @cR0w now the real delicious question is: do all the other frontier models also have killstrings, and what are they?