Main

type

5 (blog/news article)

status

21 (imported old-v2, waiting for another import)

review version

1

cleanup version

0

pending deletion

0 (-)

created at

2026-01-22 15:22:36

updated at

2026-01-22 15:22:36

Address

url

https://casco.com/blog/we-hacked-ycombinator-agents

url length

51

url crc

7399

url crc32

106962151

location type

1 (url matches target location, page_location is empty)

canonical status

2 (missing canonical tag in html)

canonical page id

-

Source

domain id

105101705

domain tld

2211

domain parts

2

originating warc id

6570684

originating url

source type

11 (CommonCrawl)

Server response

server ip

18.160.18.6

Publication date

2025-07-15 07:32:01

Fetch attempts

0

Original html size

66827

Normalized and saved size

25851

Content

title

We hacked Y Combinator's AI agents and what you can learn from it

excerpt

content

BlogWe hacked Y Combinator's AI agents and what you can learn from itWritten by Rene Brandel on Tue May 27 2025In mid-April 2025, I hacked 7 of the 16 publicly-accessible AI agents from the Y Combinator spring 2025 batch. This allowed me to leak user data, execute code remotely, and take over databases. Each vulnerability took me less than 30 minutes to exploit. TL;DR: Tool definitions and parameters were not protected by transitive authentication Poorly protected code execution tools allowed me to execute arbitrary code remotely Tools that call external endpoints enabled me to set up a malicious database configuration This type of incident isn't isolated to YC companies. 73% of enterprises experienced at least one AI-related security incident in the past 12 months. A cyber incident costs on average $4,000,000 and your AI agent could be the root cause. In this post, I'll go into the most common attack vectors and how hackers "think" when attacking your AI agent. Case #1: From leaked...

author

updated

1769938440

Text analysis

block type

0

extracted fields

105

extracted bits

featured image
title
full content
content was extracted heuristically

detected location

0

detected language

1 (English)

category id

-

index version

1

paywall score

0

spam phrases

0

Text statistics

text nonlatin

0

text cyrillic

0

text characters

4292

text words

851

text unique words

416

text lines

1

text sentences

44

text paragraphs

1

text words per sentence

19

text matched phrases

0

text matched dictionaries

0