Keycard

@KeycardAI

Keycard puts users, developers and companies in control of AI agents with real-time, adaptive permissions and complete transparency.

keycard.ai

Joined December 2024

Keycard
@KeycardAI
Aug 24
AAuth Night is coming back to SF October 15th! During AAuth Night @aiDotEngineer our CTO @jaredhanson showed how intent-based authorization (AAuth missions) can be used as a way to reduce consent fatigue and defer credential issuance until after an agent has discovered tools.
00:00
Keycard
@KeycardAI
Aug 20
The reaction to an agent escaped a sandbox or dropped a database can't be to connect it to less things because you can't trust your agents. The answer is to restrict an agent's authority, not its access. Take a look at how we secured OpenClaw for example 👇
Insecure Agents Podcast
@insecureagents
Aug 20
You Can't Just Lock an Agent in a Box: Luke Hinds, founder of nolabs and creator of Sigstore "People say it escaped a sandbox. It didn't. A sandbox is only as strong as the access that you grant to it." Luke Hinds (@decodebytes) created Sigstore, which now protects billions of
00:00
Keycard
@KeycardAI
Aug 19
During @aiDotEngineer World's Fair our Head of DevRel @KimMaida walked through 3 common agent access problems and their solutions > Agents dropping a db with an overprivileged credential > Human consent fatigue > Credential use without attribution All easily fixed with Keycard
00:00
Keycard
@KeycardAI
Aug 18
Agents are inherently goal seeking. @AhmadNassri CTO of @SocketSecurity explains what it takes to keep bad packages out of reach. We add an additional layer of depth. Our infra keeps secrets away from a compromised agent, authorizes agent actions, and revokes agent access.
Insecure Agents Podcast
@insecureagents
Aug 18
Blocking Bad Packages at the Network Level: Ahmad Nassri (Socket) on Controlling What an Agent Sees "We're also masking the visibility of those numbers and those versions' existence from the agent itself. So as far as the agent or the package manager is concerned, those versions
00:00
Keycard
@KeycardAI
Aug 17
Today agents are broadly using over scoped credentials delegated by a human. The conversations @insecureagents surfaced at @aiDotEngineer made it clear developers care about security and the best AI infra makes the secure path the easy path.
Insecure Agents Podcast
@insecureagents
Aug 17
"In the current world agents are using the credentials delegated by a human. Even that is not a trivial problem. How do those credentials get passed to that agent? Is consent collected anywhere? How do we ensure LLMs don't see those credentials?" - @juecd__ CEO of @usekernel
00:00