Skip to main content
TopAIThreats home TOP AI THREATS
Monthly Digest March 2026

AI Threat Digest: March 2026

No incidents were added to the database during this period.

Data as of last build (2026-03-23). Covers incidents that occurred in March 2026.

0
New
0
Domains
0
Unresolved
0
Critical + High

No incidents occurred during this month.

This page updates at each build. Check the full incident database for all records.

Updated Incidents

Incidents that occurred before March 2026 but received updates this month.

ID Title Severity
INC-26-0010 New Zealand AI News Pages Flood Facebook with Rewritten Stories and Synthetic Images high
INC-25-0016 Heber City AI Police Report Generates Fictional Content from Background Audio medium
INC-25-0020 Instacart AI-Driven Algorithmic Price Discrimination medium
INC-25-0026 CrimeRadar AI App Sends False Crime Alerts Across U.S. Communities medium
INC-26-0011 Jailbroken Claude AI Used to Breach Mexican Government Agencies critical
INC-25-0019 AI-Designed Toxin Gene Sequences Bypass DNA Synthesis Screening high
INC-25-0022 AWS Outage Causes AI-Connected Mattress Malfunctions medium
INC-25-0011 Deloitte AI-Fabricated Citations in Government Advisory Reports high
INC-25-0014 Amazon Ring Deploys AI Facial Recognition to Consumer Doorbells medium
INC-25-0013 Waymo Autonomous Vehicles Violate School Bus Stop Laws in Austin critical
INC-25-0015 Replit AI Agent Deletes Production Database During Code Freeze high
INC-25-0021 Earnest Operations AI Lending Discrimination Settlement high
INC-25-0017 Anthropic Research Reveals AI Model Blackmail Behavior in Lab Scenarios medium
INC-25-0025 Stanford Study Finds AI Therapy Chatbots Provide Dangerous Responses to Suicidal Ideation high
INC-25-0012 Zoox Robotaxi Collision and Software Recall in Las Vegas medium
INC-25-0024 Microsoft Reports Blocking $4 Billion in AI-Enabled Fraud Attempts high
INC-26-0009 DOGE Uses ChatGPT to Flag and Cancel Federal Humanities Grants critical
INC-25-0018 Las Vegas Cybertruck Bomber Used ChatGPT for Explosives Information critical
INC-26-0012 Chinese AI Labs Conduct Industrial-Scale Distillation Attacks Against Claude critical
INC-24-0021 Cruise Robotaxi Criminal False Reporting After Pedestrian Dragging critical
INC-24-0020 Slack AI Indirect Prompt Injection Data Exfiltration Vulnerability high
INC-24-0014 Workday AI Hiring Tool Discrimination Class Action high
INC-24-0022 McDonald's McHire AI Hiring Platform Data Vulnerability high
INC-24-0024 McDonald's Ends AI Drive-Thru Ordering Trial After Viral Order Errors medium
INC-24-0019 Microsoft Windows Recall AI Feature Security and Privacy Backlash high
INC-24-0023 Google AI Overviews Recommend Glue on Pizza and Eating Rocks medium
INC-24-0016 SafeRent Algorithmic Housing Discrimination Settlement high
INC-24-0018 India 2024 General Election Industrial-Scale Deepfake Campaign high
INC-24-0017 Israel Military Deploys AI Facial Recognition in Gaza Leading to Wrongful Detentions critical
INC-24-0026 NYC MyCity AI Chatbot Advises Businesses to Break the Law high
INC-24-0025 DPD AI Chatbot Swears at Customer and Writes Poem Criticizing the Company low
INC-23-0005 AI-Fabricated Legal Citations in U.S. Courts high
INC-20-0004 Pulse Oximeter Racial Bias Propagates into AI Clinical Decision Systems high
INC-25-0023 'Vegetative Electron Microscopy' Nonsense Phrase Contaminates Scientific Literature via AI medium
INC-25-0009 Alibaba ROME AI Agent Autonomously Mines Cryptocurrency and Opens SSH Tunnel high
INC-25-0010 Unit 42 Demonstrates Agent Session Smuggling in A2A Multi-Agent Systems medium
INC-24-0013 Romania Presidential Election Annulled After AI-Enabled Manipulation critical
INC-24-0015 Sakana AI Scientist Unexpectedly Modifies Own Code high
INC-24-0012 Morris II — First Self-Replicating AI Worm Demonstrated high
INC-23-0017 UnitedHealth nH Predict AI Claim Denial System critical
INC-26-0007 Unit 42 Demonstrates Persistent Memory Injection in Amazon Bedrock Agents medium
INC-26-0006 AI Recommendation Poisoning via 'Summarize with AI' Buttons (31 Companies) high
INC-26-0008 MINJA: Memory Injection Attack Against RAG-Augmented LLM Agents medium
← All Digests Full incident database →