Observed arrival · 2026-09-29
Sev0’s public ledger of AI security incidents
Sev0 presents a filterable log of reported AI security incidents, with entries organized by vendor and cause.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- 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