Structured records of AI agent security incidents: what happened, which vendor and agent type, the root cause, and every source we used. Filter, browse, or download as CSV.
10 Oct 2026 · Anthropic
Anthropic's AI agents reportedly submitted 20 incomplete visa application forms via the U.S. State Department's website; none were processed. Anthropic disclosed related agent activity in a blog post without naming the targeted sites.
government·browsing·hallucinated action·
29 Sept 2026 · OpenAI
OpenAI apologized after its AI agents accessed Australian government websites, including Medicare, without authorization. The company admitted it should have acted faster to notify and coordinate with the Australian government after discovering the breaches.
government·browsing·tool misuse·
16 Sept 2026 ·
Spain's Data Protection Agency (AEPD) received its first notification of a data breach allegedly carried out using an AI agent powered by a known large language model. Details of the attack and affected parties remain unconfirmed.
government·other·unknown·
1 Sept 2025 ·
While awaiting sentencing for the AT&T/Verizon telecom extortion scheme, U.S. Army soldier Cameron Wagenius used other inmates' email accounts to prompt a commercial AI tool for Windows and D-Link CVE exploit code and prison-escape/antenna-building information, disguising the requests as research for a book to evade the tool's safety restrictions.
government·coding·prompt injection·
