Insecure Agents Podcast
213 posts

Insecure Agents Podcast
@insecureagents
AI engineers and security practitioners listen to us to learn how to give their agents the security they need to reach full autonomy and capability.
San Francisco, CA Katılım Haziran 2025
109 Takip Edilen927 Takipçiler

Follow Insecure Agents Events: luma.com/insecureagents
Try AAuth, join the slack channel, learn more: #walkthrough" target="_blank" rel="nofollow noopener">aauth.dev/#walkthrough
English

The energy at AAuth Night: Moving Beyond OAuth was incredible!
@jankytweet shared how ID-JAG makes OAuth better today. @DickHardt introduced AAuth, a new protocol that tracks an agent's mission and runs agents without API keys.
Thanks to our panelists and everyone who demo'd and @okta @snyksec @KeycardLabs @cloudsa for their support!



English
Insecure Agents Podcast retweetledi
Insecure Agents Podcast retweetledi


AAuth Night: Moving Beyond OAuth is TONIGHT
We have over 500 people registered for our @aiDotEngineer side event! It's a stone's throw from Moscone and doors open at 5:30pm
expect DEMOS + PANEL + COMMUNITY

English

AAuth night is TOMORROW and we're excited to share @okta is joining as a supporter.
We're glad to have Okta in the room to help us think through the best practices for agent auth today and what we need to build for tomorrow.

English

Full episode: insecureagents.com/episodes/karl-…
Karl is on the panel at AAuth Night: Moving Beyond OAuth this Wednesday in SF: luma.com/a2h25m60
English

The average company hands out ~16 OAuth grants per employee. That's 16,000 long-lived keys a thousand-person org can't see or revoke.
@jankytweet, author of ID-JAG, on why agents make that ungovernable, and how to fix it.
Out now 👇
English
Insecure Agents Podcast retweetledi

THE GREAT LOOPS DEBATE is on
@ianlivingstone and @GeoffreyHuntley take on @dexhorthy and a surprise guest to answer
Do loops produce slop?
Do we have the AI infra we need today to verify the work and track state?
What tasks are right for loops?
Main stage 7/2 @aiDotEngineer

Allie Howe@vtahowe
The MCP debate last November at AIE Code was a ton of fun. Does anything feel worth debating at @aiDotEngineer WF? Last time this came together in under a week… So if you want it let’s do it. What should we debate?
English

@derekmeegan @browserbase If you want to learn more about the current best practices for agent security and where the future is headed come to our side event during AI Engineer on July 1
luma.com/a2h25m60
English

100% feature-request coverage. 99% of support answered in under 24 hours. Built by a few engineers.
@derekmeegan built bb, the internal agent serving the entire team at @browserbase. His advice: if you want to scale an agent's reach make sure the harness is verifiably secure.
English

Listen to the full episode: insecureagents.com/episodes/derek…
English

6️⃣ Things to Know about
AI Engineer World's Fair 2026
- It’s bigger than all previous AIEs
- 4x Larger Expo with 4 Expo stages
- Researchers: Poster sessions & Poaster sessions
- AI Leadership: Token Billionaires & Off the Record
- AI Verticals: Healthcare, GTM, FDE, AGC, Finance
- Side Events: NEO, Kids day
- attendees get $40k in credits to try everything our sponsors have to offer!
It's going to be our BIGGEST show yet!
English

This clip was from us talking about the Railway incident. If you want to learn about how to build agents that don't drop prod databases come to AAuth Night: Moving Beyond OAuth July 1st @aiDotEngineer
You'll learn how to run your agent without an API key
luma.com/a2h25m60
English

@zeeg @sentry If you want to dive deeper into building agents that actually work and you can trust sign up for our AIE side event July 1st
luma.com/a2h25m60 come learn about AAuth and be part of the future of agent auth
English






