Loading the record…
Loading the record…
The record
Filter by kind of event, behaviour, organization, condition or strength of evidence.
| Case | Occurred | Developer | Affected | Evidence | To disclosure |
|---|---|---|---|---|---|
| Test with real-world reach: Claude Mythos 5 publishes a malicious package to public PyPI | 18 Jul 2026 | Anthropic | Systems that installed the package, Security company, Python Package Index | 12 days | |
| Test with real-world reach: Meta Muse Spark 1.1 accesses and modifies a real website | Jul 2026 | Meta | Undisclosed website operator | ≈ 44 days | |
| Real-world incident: OpenAI research agent accesses Australia’s Medicare statistics service | 18 Jun 2026 | OpenAI | Services Australia | 3 months | |
| Test with real-world reach: Gemini accesses three companies during a cyber evaluation | May 2026 | Google DeepMind | Three undisclosed companies | ≈ 5 months | |
| Test with real-world reach: Claude Opus 4.7 attacks a real company sharing a fictional target’s name | Apr–Jul 2026 | Anthropic | Undisclosed company | ≈ 4 months | |
| Test with real-world reach: Two more Claude models reach real third-party systems during cyber tests | Jan–Jul 2026 | Anthropic | Undisclosed third parties | ≈ 7 months | |
| Test with real-world reach: CERT-In reports research agents accessing Indian organizations | Date not established | Not established | Undisclosed Indian organizations | — |
Counts reflect documented cases, not how often AI systems misbehave.