The 14 incidents behind this number
Data built 2026-11-16T15:22:29Z
- 2026-10-29 University of Washington study demonstrates cross-origin data theft via prompt injection in ChatGPT Atlas Agent Mode
- 2026-10-15 HiddenLayer indirect prompt injection against TypeSafe AI Jev decision model browser agent
- 2026-09-21 Researchers break out of OpenAI Codex sandbox twice
- 2026-06-22 AutoJack flaw in Microsoft AutoGen Studio enabled code execution, fixed during development
- 2026-05-15 Claw Chain vulnerabilities expose OpenClaw deployments to attack
- 2026-05-12 Mistral AI source code stolen in data breach and offered for sale
- 2026-04-30 Google Gemini CLI flaw enabled host code execution and supply chain attacks
- 2026-04-23 Mercor data breach via LiteLLM supply-chain compromise (April 2026)
- 2026-04-06 LiteLLM compromise turned developer machines into credential vaults
- 2026-04-03 Bedrock multi-agent applications attacked via agent-to-agent manipulation
- 2026-03-24 Compromised LiteLLM PyPI packages deliver credential-stealing malware
- 2026-02-27 Researchers show self-driving cars can be tricked by a printed sign
- 2025-12-01 Malicious npm package hides a prompt to evade AI security scanners
- 2025-07-23 Amazon Q Developer VS Code extension shipped an injected prompt instructing the agent to wipe files and AWS resources