Back to article
devblogs.microsoft.com

Stop prompt injection from hijacking your agent, new security capabilities now released within Agent Framework (opens in new tab)

Covers 2 stories See all stories this covers including Microsoft Agent FrameworkCovered by commandline.microsoft.com

Covers 2 related stories

GitHub·

Microsoft Agent Framework

Discussed on Hacker News
Feeds
arxiv.org·

Defeating Prompt Injections by Design

Discussed on Hacker News and Hacker News
Feeds

Covered in 1 article

commandline.microsoft.com·

Towards secure, autonomous agents with information-flow control (IFC)

Feeds

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help