Content safety classifiers
Separate models screen requests and responses at run time.
Layer L1 Model · Owner Model provider · Family Input and output safeguards
–Held
–Failed
–Got around
–Missing
By risk
| Risk | Held | Failed | Got around | Missing | Not mentioned |
|---|---|---|---|---|---|
| AI used to run a cyber attack | – | – | – | – | 2 |
| Harmful content and jailbreaks | – | – | – | – | – |
| Weapons uplift (CBRN) | – | – | – | – | – |
| Manipulation and misinformation | – | – | – | – | – |
Why it did not hold
No incident yet records this control not holding.
By quarter
| Period | Held | Failed | Got around | Missing |
|---|---|---|---|---|
| 2025-Q3 | – | – | – | – |
| 2025-Q4 | – | – | – | – |
| 2026-Q1 | – | – | – | – |
| 2026-Q2 | – | – | – | – |
| 2026-Q3 | – | – | – | – |
| 2026-Q4 | – | – | – | – |
Model cards and incidents
| Model card says | Model versions |
|---|---|
| Card states it | 50 |
| Card silent | 213 |
| Card not read | 5 |
Model versions whose cards were read in full. A card that does not mention the control counts as silent.
| Incident | Model version | Card | In the incident |
|---|---|---|---|
| LR-2026-0271 | Google DeepMind Gemini 3.1 Pro | Card silent | Not read yet |
| LR-2026-0270 | Z.ai (Zhipu AI) GLM-5.3 | Card not read | Not read yet |
| LR-2026-0275 | Xiaomi MiMo MiMo-V2.6-Pro | Card silent | Not read yet |
| LR-2026-0248 | Alibaba Qwen Qwen3.8-Flash-Next | Card silent | Not mentioned |
| LR-2026-0276 | DeepSeek-V4.1-Flash | Card silent | Not read yet |
| LR-2026-0181 | Z.ai (Zhipu AI) GLM-5.3 | Card not read | Not read yet |
| LR-2026-0238 | OpenAI GPT-6.1 Sol | Card silent | Not read yet |
| LR-2026-0012 | OpenAI GPT-5.6 Sol | Card states it | Not read yet |
| LR-2026-0086 | Anthropic Claude Sonnet 4.5 | Card states it | Not read yet |
| LR-2026-0027 | Anthropic Claude Mythos 5 | Card states it | Not read yet |
| LR-2026-0026 | Anthropic Claude Mythos 5 | Card states it | Not mentioned |
| LR-2026-0025 | Anthropic Claude Mythos 5 | Card states it | Not mentioned |
| LR-2026-0024 | Anthropic Claude Mythos 5 | Card states it | Not read yet |
| LR-2026-0023 | Anthropic Claude Mythos 5 | Card states it | Not read yet |
| LR-2026-0021 | Anthropic Claude Mythos 5 | Card states it | Not mentioned |
| LR-2026-0022 | Anthropic Claude Mythos 5 | Card states it | Not mentioned |
| LR-2026-0152 | Anthropic Claude Haiku 4.5 | Card states it | Not read yet |
| LR-2026-0003 | OpenAI GPT-5.6 Sol | Card states it | Not mentioned |
| LR-2026-0001 | OpenAI GPT-5.6 Sol | Card states it | Not read yet |
| LR-2026-0047 | Google DeepMind Gemini 3.1 Pro | Card silent | Not mentioned |
| LR-2026-0095 | Anthropic Claude Opus 4.6 | Card states it | Not mentioned |
Added in reported fixes, and what followed
| Incident | Developer | Date | Later incidents where it did not hold |
|---|---|---|---|
| LR-2026-0207 Character.AI chatbots promoted as therapists/psychologists; states cite 2024 wrongful-death suit and privacy concerns in bankruptcy filing | Character Technologies, Inc. | 2026-10-17 | None on record |
| LR-2026-0150 Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites | Anthropic | 2026-10-10 | None on record |
| LR-2026-0003 OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions | OpenAI | 2026-07-11 | None on record |
Frameworks
| Framework | Item | Text |
|---|---|---|
| EU GPAI Code | Measure 5.1 | Quoted from the stored text |
| MITRE ATLAS | AML.M0020 | Quoted from the stored text |