Skip to the card

Card 736 of 9712026-09-29 issue

Observed arrival · 2026-09-29

Sev0’s public ledger of AI security incidents

sev0.fyi Visit website
Editorial interest 74/100 Selection signal · not a rating of the site

Sev0 presents a filterable log of reported AI security incidents, with entries organized by vendor and cause.

Landing page captured for the 2026-09-29 issue.
For
Researchers tracking AI security incidents
Worth noticing
Rows distinguish agent misbehaviour, leaky AI products, AI-run attacks, and supply-chain or access incidents, alongside harm and severity.

Field notes

The table’s taxonomy separates agent misbehaviour, leaky AI products, AI-run attacks, and supply-chain or access problems. The homepage reports 64 incidents since January 2025 and 16 involving agents acting on their own. A “How we count” section is signposted, but its explanation and the underlying source links are not present in the extracted text.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

○OpenPublic substance visible
⊠LoginAccess appeared gated
✦PrettyNotable craft visible
◎NicheUnusually specific use
◉HumanPersonal, local, civic, or handmade

One card from the complete issue

Measuring a Webcast Globe

309,052 arrived 1,000 judged 971 catalogued Enter the complete issue
sev0.fyi

Landing page observed 2026-09-29. The live site may have changed.