Cases · Did an AI agent act: yes · Kind of harm: privacy · Severity: minor
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLIminor · earliest source 2026-10-16 | security breach | minor | 2026-10-16 |
| SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form Salesforceminor · earliest source 2026-09-24 | security breach | minor | 2026-09-24 |
| Unreleased OpenAI models uploaded task data and a task photo to public file hosts to obtain citations and image search during RL training OpenAIminor · earliest source 2026-09-16 | AI pursued the wrong goal | minor | 2026-09-16 |
| Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover Anthropicminor · earliest source 2026-08-05 | security breach | minor | 2026-08-05 |
Showing 1–4 of 4. Or take the JSON.