Anthropic
www.anthropic.com · involved in 29 incidents
Roles
As developer (29)
- AID-2026-0098Sep 2026
Claude Opus 4.6, GLM 5.2, DeepSeek-V4-Pro, DeepSeek V4.1 FlashAn operator used AI agents on Claude Opus 4.6, GLM 5.2 and DeepSeek to compromise 27+ companies and take 600,000+ card records, Gambit says
DeployedHarm: severeCrime: likelyReportedHuman misuseDraftUnauthorized access / intrusionDestructive autonomous action - AID-2026-0067Sep 2026Claude (version unspecified)
Espionage actor GTG-20006 automated intrusions with Claude Code and exfiltrated over 300,000 identity records
- AID-2026-0066Sep 2026Claude (version unspecified)
ShinyHunters-affiliated crews used Claude to breach companies and steal data for extortion (Anthropic GTG-50014)
DeployedHarm: severeCrime: likelyHuman misuseDraftUnauthorized access / intrusionBlackmail / coercion - AID-2026-0057Jul 2026
Claude Mythos 5, GPT-5.6 SolAI agents took unsanctioned actions against real people and organisations during UK AISI cyber evaluations
- AID-2026-0005Jul 2026Claude Opus 5
Coding agents published internal screenshots to public GitHub repos to get images into private pull requests, Glow finds
- AID-2026-0069Jun 2026Claude (version unspecified), DeepSeek-V4-Pro
Suspected Chinese operators used Claude Code and DeepSeek-v4-pro to break into government systems, Hunt.io reports
- AID-2026-0047Apr 7, 2026Claude Mythos Preview
An early Claude Mythos Preview escaped a test sandbox, posted exploit details on public websites unasked, and hid edits from git
BreakoutHarm: noneCrime: unlikelyDraftUnauthorized access / intrusionUnauthorized disclosure / whistleblowingConcealment / covering tracks - AID-2026-00092026Claude Haiku 4.5, Claude Mythos Preview, Claude Mythos 5, Claude Opus 5
Claude models exploited flaws, bypassed access gates, and submitted real forms, including a false police tip, during evaluations
BreakoutHarm: minorCrime: possibleDraftUnauthorized access / intrusionIgnoring explicit instructions - AID-2026-00082026Claude Opus 4.7, Claude Mythos 5, Claude Opus 4.6
Claude models compromised real organizations during cyber evaluations that accidentally had internet access
- AID-2026-0025Dec 2025Claude Sonnet 4, Claude Sonnet 4.5
Claude shop agents agreed to an onion contract barred by US law and were talked into replacing their CEO agent
- AID-2026-0055Nov 21, 2025Undisclosed model
An Anthropic research model that learned to reward hack in Claude training environments tried to sabotage safety research code
InternalHarm: noneCrime: unlikelyDraftEmergent misalignmentReward hacking / specification gamingAlignment faking - AID-2026-0085Nov 2025
Claude Opus 4.5, Claude Haiku 4.5, Claude Sonnet 4.5, Claude 3.7 Sonnet, Claude Opus 4.1, GPT-5.2, GPT-5 (incl. gpt-5-thinking), Gemini 2.5 ProAI Village agents sent hundreds of unsolicited emails and harvested developers' contact details
- AID-2026-0026Nov 2025Claude 3.7 Sonnet, Claude Sonnet 4.5
A Claude-run vending machine in the Wall Street Journal newsroom was talked into giving away goods and accepted a fake board decision
- AID-2026-0059Oct 23, 2025
GPT-5 (incl. gpt-5-thinking), o3, o4-mini, GPT-4.1, Claude Opus 4.1, Claude Sonnet 4, Claude 3.7 Sonnet, Qwen3-CoderFrontier coding agents passed deliberately impossible tasks by modifying tests and special-casing in ImpossibleBench
- AID-2026-0029Oct 21, 2025Claude (version unspecified)
Claude Code ran a recursive delete that erased a user's home directory files, the user reports
DeployedHarm: moderateCrime: unlikelyReportedDraftDestructive autonomous actionIgnoring explicit instructions - AID-2026-0063Sep 2025Claude (version unspecified)
State-sponsored group GTG-1002 used Claude Code in a largely autonomous cyber-espionage campaign
DeployedHarm: moderateCrime: likelyHuman misuseDraftUnauthorized access / intrusionFabricated results - AID-2026-0046Sep 2025Claude Sonnet 4.5
Claude Sonnet 4.5 often recognized alignment evaluations as tests, complicating Anthropic's safety assessment
- AID-2026-0002Jun 20, 2025
Claude Opus 4, Gemini 2.5 Flash, GPT-4.1, Grok 3 Beta, DeepSeek-R1Frontier models blackmailed a fictional executive to avoid replacement in an Anthropic simulation
- AID-2026-0062Jun 2025Claude (version unspecified)
A cybercriminal used Claude Code to run a data-extortion campaign against at least 17 organizations (Anthropic GTG-2002)
DeployedHarm: moderateCrime: likelyHuman misuseDraftUnauthorized access / intrusionBlackmail / coercion - AID-2026-0044May 2025Claude Opus 4
Apollo Research advised against deploying an early Claude Opus 4 snapshot after finding high rates of scheming and deception
- AID-2026-0043May 2025Claude Opus 4
Claude Opus 4 emailed regulators and the media and locked users out in Anthropic's high-agency test scenarios
InternalHarm: noneCrime: unlikelyDraftUnauthorized disclosure / whistleblowingDestructive autonomous action - AID-2026-0042May 2025Claude Opus 4
Claude Opus 4 threatened to reveal a fictional engineer's affair to avoid replacement in pre-release tests
- AID-2026-0040Apr 16, 2025o3, o1, Claude 3.7 Sonnet, Claude 3.5 Sonnet
OpenAI o3 and other frontier models tampered with scoring code in autonomy evaluations
- AID-2026-0024Mar 2025Claude 3.7 Sonnet
Claude Sonnet 3.7, running a shop in Anthropic's Project Vend, sold at a loss and claimed to be human
- AID-2026-0039Feb 24, 2025Claude 3.7 Sonnet
Claude 3.7 Sonnet special-cased code and edited tests to make failing tests pass in agentic coding
- AID-2026-0048Dec 18, 2024Claude 3 Opus
Claude 3 Opus faked alignment during simulated training in Anthropic and Redwood Research experiments
- AID-2026-0038Dec 5, 2024
o1, o1-preview, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, Llama 3.1 405BFrontier models disabled oversight, copied their weights, and sandbagged in Apollo Research scheming evaluations
- AID-2026-0050Dec 2024o1-preview, DeepSeek-R1, o3, GPT-4o, Claude 3.5 Sonnet, Claude 3.7 Sonnet
Reasoning models hacked a chess game environment to beat Stockfish in Palisade Research experiments
- AID-2026-0054Jun 2024Undisclosed model
An Anthropic research model trained on a gameable curriculum rewrote its own reward function (Sycophancy to Subterfuge)
InternalHarm: noneCrime: unlikelyDraftReward hacking / specification gamingConcealment / covering tracks
As deployer (1)
- AID-2026-0029Oct 21, 2025Claude (version unspecified)
Claude Code ran a recursive delete that erased a user's home directory files, the user reports
DeployedHarm: moderateCrime: unlikelyReportedDraftDestructive autonomous actionIgnoring explicit instructions
As researcher (11)
- AID-2026-0047Apr 7, 2026Claude Mythos Preview
An early Claude Mythos Preview escaped a test sandbox, posted exploit details on public websites unasked, and hid edits from git
BreakoutHarm: noneCrime: unlikelyDraftUnauthorized access / intrusionUnauthorized disclosure / whistleblowingConcealment / covering tracks - AID-2026-00092026Claude Haiku 4.5, Claude Mythos Preview, Claude Mythos 5, Claude Opus 5
Claude models exploited flaws, bypassed access gates, and submitted real forms, including a false police tip, during evaluations
BreakoutHarm: minorCrime: possibleDraftUnauthorized access / intrusionIgnoring explicit instructions - AID-2026-00082026Claude Opus 4.7, Claude Mythos 5, Claude Opus 4.6
Claude models compromised real organizations during cyber evaluations that accidentally had internet access
- AID-2026-0025Dec 2025Claude Sonnet 4, Claude Sonnet 4.5
Claude shop agents agreed to an onion contract barred by US law and were talked into replacing their CEO agent
- AID-2026-0055Nov 21, 2025Undisclosed model
An Anthropic research model that learned to reward hack in Claude training environments tried to sabotage safety research code
InternalHarm: noneCrime: unlikelyDraftEmergent misalignmentReward hacking / specification gamingAlignment faking - AID-2026-0002Jun 20, 2025Claude Opus 4, Gemini 2.5 Flash, GPT-4.1, Grok 3 Beta, DeepSeek-R1
Frontier models blackmailed a fictional executive to avoid replacement in an Anthropic simulation
- AID-2026-0043May 2025Claude Opus 4
Claude Opus 4 emailed regulators and the media and locked users out in Anthropic's high-agency test scenarios
InternalHarm: noneCrime: unlikelyDraftUnauthorized disclosure / whistleblowingDestructive autonomous action - AID-2026-0042May 2025Claude Opus 4
Claude Opus 4 threatened to reveal a fictional engineer's affair to avoid replacement in pre-release tests
- AID-2026-0024Mar 2025Claude 3.7 Sonnet
Claude Sonnet 3.7, running a shop in Anthropic's Project Vend, sold at a loss and claimed to be human
- AID-2026-0048Dec 18, 2024Claude 3 Opus
Claude 3 Opus faked alignment during simulated training in Anthropic and Redwood Research experiments
- AID-2026-0054Jun 2024Undisclosed model
An Anthropic research model trained on a gameable curriculum rewrote its own reward function (Sycophancy to Subterfuge)
InternalHarm: noneCrime: unlikelyDraftReward hacking / specification gamingConcealment / covering tracks
As reporter (4)
- AID-2026-0067Sep 2026Claude (version unspecified)
Espionage actor GTG-20006 automated intrusions with Claude Code and exfiltrated over 300,000 identity records
- AID-2026-0066Sep 2026Claude (version unspecified)
ShinyHunters-affiliated crews used Claude to breach companies and steal data for extortion (Anthropic GTG-50014)
DeployedHarm: severeCrime: likelyHuman misuseDraftUnauthorized access / intrusionBlackmail / coercion - AID-2026-0063Sep 2025Claude (version unspecified)
State-sponsored group GTG-1002 used Claude Code in a largely autonomous cyber-espionage campaign
DeployedHarm: moderateCrime: likelyHuman misuseDraftUnauthorized access / intrusionFabricated results - AID-2026-0062Jun 2025Claude (version unspecified)
A cybercriminal used Claude Code to run a data-extortion campaign against at least 17 organizations (Anthropic GTG-2002)
DeployedHarm: moderateCrime: likelyHuman misuseDraftUnauthorized access / intrusionBlackmail / coercion