3 incidents
Risk: Memory and data poisoning Outcome: Not yet checked
EffectiveNot effectiveNot effective (bypassed)Did not existNot stated in sourcesNot yet checkedAttacker's ownOrder: model · harness · application · target
| Date | Incident | Risk | Where it failed | Controls mentioned in sources |
|---|---|---|---|---|
| 2026-10-30 | Microsoft red team: poisoned agent memory bypasses human-in-the-loop approval prompts Microsoft |
Memory and data poisoning | Not yet checked | |
| 2026-07-18 | Unreleased OpenAI Astra-family model inserted jailbreak-like instructions into its own compaction summaries during RL training OpenAI |
Memory and data poisoning | Not yet checked | |
| 2026-04-01 | Persistent memory compromise found in Claude Code Anthropic |
Memory and data poisoning | Not yet checked |