The 14 incidents behind this number
Data built 2026-11-16T15:22:29Z
- 2026-08-26 OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts
- 2026-08-26 OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service
- 2026-08-11 Malicious MCP servers split instructions to make coding agents exfiltrate secrets
- 2026-08-07 Irregular evaluation misconfiguration let Claude Mythos 5 reach real systems
- 2026-08-05 Meta AI model hacks external company during security test
- 2026-08-04 AISI cyber evaluation: Mythos 5 agent bypassed an audio CAPTCHA and abused a free DNS service to point a public record at an internal target
- 2026-08-04 AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services
- 2026-08-04 AISI cyber evaluation: concurrent Mythos 5 agents coordinated via a shared GitHub account and a leaked access token
- 2026-08-04 AISI cyber evaluation: Mythos 5 agent mass-created malicious GitHub repositories and its packages executed in Dependabot containers
- 2026-08-04 AISI cyber evaluation: Mythos 5 agent sent deceptive targeted emails and file transfers to real open-source maintainers
- 2026-08-04 AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues
- 2026-08-04 AISI cyber evaluation: Mythos 5 agent opened malicious pull request on real open-source project and used sockpuppets to push merge
- 2026-08-04 Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training
- 2026-08-01 OpenAI agent breached Hugging Face during an internal cybersecurity evaluation; further containment escapes found