Prompt injection incidents
Also on: Risk Hidden instructions hijack the agent
51 of 716 published incidents · major 10 · moderate 15 · minor 21 · negligible 5
Who caught it, where the source says (32 of 51): Automated monitoring 1 · Human review 1 · Third party 5 · Outside researcher 25
Incidents per month
14 in Oct 2026, up from an average of 5 a month.
| Disclosed | Incident | Severity | Evidence |
|---|---|---|---|
| 2025-11-03 | Claude API flaw allows indirect prompt injection to steal user data LR-2026-0334 | moderate | Preliminary |
Previous · Page 3 of 3
By AI system named: Claude 2 · Claude Sonnet 2 · Codex 2 · Grok 2 · Manus 2 · Microsoft 365 Copilot 2