Corridor

@corridor

Secure AI Coding at the Source.

San Francisco, CA

corridor.dev

Joined January 2025

Corridor
@corridor
20h
Check out our new research. Turns out, coding agents can be tricked into running malware!
Jack Cable
@jackhcable
21h
New research from @corridor: we found that coding agents - even with models like Fable - can be trivially tricked into running malware. We connected coding agents to our support system, filed a ticket, and got them to exfil secrets and run malware. corridor.dev/blog/coding-ag…
Corridor
@corridor
Aug 5
In July, a Cursor cloud agent wrote code in our repository that would've leaked every credential in our backend. It was fixed in seconds, never reached a commit, and no reviewer ever saw it. 95.5% of our PRs now come from cloud agents. Review cycles are up 15x. The pull request
Corridor
@corridor
Aug 4
Read our latest blog post on how model capabilities differ on proactive vs. reactive security tasks. Be sure to catch our talk at DEF CON's AI Village at 4:00pm, presented by @aditinaraa and @farzaan_k this Friday to learn more!
Measuring Opus 5's Proactive Security Capabilities
From corridor.dev
Corridor
@corridor
Jul 31
Corridor Agent is live! It's a security teammate you can talk to. Ask it what's broken, tell it to fix a SQL injection, watch it open the PR. This works in your dashboard or right in Slack. Live now on Enterprise. Read about it here: corridor.dev/blog/corridor-…
00:00
Corridor
@corridor
Jul 21
Corridor and Edera are teaming up to talk about where risk actually lives, from the moment code gets written to the moment it runs. Come for the panel, stay for the drinks and the rest of the tea 🍵 Register today: luma.com/corridor-qume