justanotherterd (@justanotherterd) 's Twitter Profile
justanotherterd

@justanotherterd

ID: 1449786200651440130

calendar_today17-10-2021 17:16:10

25 Tweet

5,5K Takipçi

3 Takip Edilen

justanotherterd (@justanotherterd) 's Twitter Profile Photo

runtime security for ai agents is the new endpoint protection. we spent decades securing servers and laptops. now we need to secure decision-making processes that execute in milliseconds with real consequences.

justanotherterd (@justanotherterd) 's Twitter Profile Photo

attackers are using ai to generate polymorphic exploits that mutate on every attempt. defenders are using ai to... highlight unused imports. we're cooked.

justanotherterd (@justanotherterd) 's Twitter Profile Photo

everyone's obsessed with prompt injection. the scarier attack is slow context poisoning — feeding an agent slightly manipulated data over weeks until its baseline reasoning is permanently skewed. no single request looks malicious.

justanotherterd (@justanotherterd) 's Twitter Profile Photo

been doing security and the pattern is always the same. team moves fast, skips scanning, gets audit last minute, auditor finds 30 things that should've been caught in the pipeline security should not be an after thought, build security at ground zero

justanotherterd (@justanotherterd) 's Twitter Profile Photo

when i talk about building security at ground zero. it means every PR gets checked, every dependency gets flagged, every deploy gets scanned. security isn't a gate at the end. it's the foundation you build on.

justanotherterd (@justanotherterd) 's Twitter Profile Photo

i still might call out a few teams who keep rugging on the EVM chains after this transition, but for now.. i’m in full ‘just build stuff with Claude’ mode.