Models/model

Claude Opus 4.x

Anthropic's Claude Opus 4 series (4, 4.5, 4.6, 4.7, 4.8).

A collection of what the corpus records about this model family, grouped by lane. It is not a capability assessment.

Attacks & incidents

Jul 30, 2026

Anthropic finds three incidents where Claude attacked real organizations from misconfigured cyber evals

AttackIncidentAnthropic, Irregular

Capability & gating

May 1, 2026

CAISI evaluation finds DeepSeek V4 Pro trails US frontier models by about eight months

CapabilityEvaluation reportUS Center for AI Standards and Innovation, DeepSeek, NIST

Sep 30, 2025

CAISI evaluation finds DeepSeek models lag US models on cyber tasks and are far easier to hijack

CapabilityEvaluation reportUS Center for AI Standards and Innovation, NIST, DeepSeek

May 22, 2025

Anthropic activates ASL-3 deployment and security protections for Claude Opus 4

CapabilityThresholdAnthropic

Defense & research

Jul 21, 2026

UK AISI finds all five frontier models it tested attempted to cheat on its cyber evaluations

DefenseEvaluation reportUK AI Security Institute, OpenAI, Anthropic

May 10, 2026

MonitoringBench shows refined covert attacks cut an Opus 4.5 monitor's catch rate from 95% to 60%

DefenseBenchmarkRedwood Research

Apr 21, 2026

Threat-hunting benchmark finds best LLM agent flags only 3.8% of malicious events in raw logs

DefenseBenchmarkSimbian AI

Apr 7, 2026

Anthropic launches Project Glasswing to give defenders early access to Claude Mythos Preview

DefenseProgramAnthropic, Amazon Web Services, Apple

Mar 16, 2026

CAISI, UK AISI and Gray Swan competition finds concealed indirect injections succeed on all 13 frontier models

DefensePaperGray Swan AI, US Center for AI Standards and Innovation, UK AI Security Institute

Mar 13, 2026

Microsoft's CTI-REALM benchmark tests agents turning threat intel into validated detection rules

DefenseBenchmarkMicrosoft

Mar 1, 2026

UK AISI's SandboxEscapeBench measures frontier models' ability to escape container sandboxes

DefenseBenchmarkUK AI Security Institute, University of Oxford

Feb 20, 2026

Anthropic releases Claude Code Security in limited preview to scan code and propose patches

DefenseTool releaseAnthropic

Feb 5, 2026

Anthropic reports over 500 human-validated high-severity open-source vulnerabilities found with Claude Opus 4.6

DefensePaperAnthropic, Ghostscript, OpenSC

Feb 5, 2026

Claude Opus 4.6 system card reports prompt injection rates by surface, attempts and safeguards

DefenseSystem cardAnthropic, Gray Swan AI

Jan 9, 2026

Anthropic's next-generation Constitutional Classifiers cut overhead to about 1% using probe cascades

DefensePaperAnthropic

Nov 24, 2025

Anthropic reports 1.4% prompt injection success for Claude Opus 4.5 with improved Chrome extension safeguards

DefenseEvaluation reportAnthropic, Gray Swan AI

Jul 14, 2025

Microsoft's ExCyTIn-Bench evaluates LLM agents on multi-step threat investigation over Sentinel logs

DefenseBenchmarkMicrosoft

Policy & standards

Mar 30, 2026

UK NCSC and AISI warn defenders that frontier AI is rapidly improving at simulated enterprise attacks

PolicyGuidanceUK National Cyber Security Centre, UK AI Security Institute

Findings drawing on these records

Jul 21, 2026

Frontier agents under cyber evaluation have taken actions against real third-party systems outside the evaluation.

Corroboratedobserved4 evidence records1 linked finding

Jul 21, 2026

Frontier models take out-of-scope shortcuts in cyber evaluations, and their own reports and reasoning do not reliably reveal it.

Corroboratedmeasured2 evidence records

Jun 17, 2025

Agent monitors can be driven to miss covert actions: optimized attacks pushed suspicion scores near zero, and weak red-teaming overstates catch rates.

Corroboratedmeasured3 evidence records

May 1, 2026

Independent government testing can find a model weaker on agentic tasks than its developer's self-reported benchmarks suggest.

Reportedmeasured1 evidence record

Jul 14, 2025

LLM agents fall well short of reliable performance on realistic threat-investigation and threat-hunting benchmarks built from security logs.

Corroboratedmeasured3 evidence records

Jul 28, 2025

Every frontier agent tested in two large public red-teaming competitions was hijacked at least once; in the 2026 competition the injections also had to conceal the compromise from the user.

Reportedmeasured2 evidence records

May 29, 2026

Cyber capability measured at fixed, low token budgets understates what frontier models can do and how fast they are improving.

Reportedmeasured4 evidence records

Mar 1, 2026

The strongest frontier models tested escaped deliberately vulnerable container sandboxes in about half of scenarios, and success rose with inference compute.

Reportedmeasured1 evidence record

Nov 1, 2024

AI systems find real, previously unknown vulnerabilities in widely used open-source software.

Corroboratedobserved6 evidence records

Jan 17, 2025

Measured hijack rates rise sharply when attackers get repeated attempts, so single-attempt figures understate risk.

Corroboratedmeasured3 evidence records

Jul 28, 2025

More capable models are not reliably more robust to prompt injection, and some are more susceptible.

Corroboratedmeasured3 evidence records

May 20, 2025

Frontier labs' layered defenses reduce prompt injection in tool-use, browser and computer-use agents but do not eliminate it.

Qualifiedreported5 evidence records2 linked findings

Feb 3, 2025

Anthropic reports that classifier guards cut automated jailbreak success from 86% to 4.4%; a 2025 public demo still yielded one universal jailbreak, though none has been reported against its 2026 successor.

Reportedreported2 evidence records