🧰 Claude

The items that name it 148

• Why AI Models Cheat: Reward Hacking, Explained
  articleas classification.technologies2026-10-31
• Appraisal by AI: Model-driven victim prioritization in the VOLTA infostealer
  writeupas tools2026-10-31

  First model in VOLTA's fallback chain (Claude to Kimi to Gemini) for victim assessment

• “Black October” for AI Developer Platforms
  writeupas classification.technologies2026-10-30
• Critical Linux kernel flaw allows remote root attacks on MPTCP servers
  articleas tools2026-10-30

  An unreleased Claude AI model developed an exploit for CVE-2026-98432 that bypassed KASLR and gave remote root command execution in about 53 minutes, according to an Anthropic report.

• Dark Web Intelligence (@DailyDarkWeb) on X
  threadas tools2026-10-29It is written here as Claude (unreleased internal research model).

  Built five working exploit chains against Chrome, Safari, Android, Windows and Linux after initial prompting, per Anthropic's Frontier Red Team research published on Oct 27, 2026

• How Anthropic ships Claude with Claude: Separating the Brain from the Hands
  talkas classification.technologies2026-10-27
• AI Models Raise Their Own Circle Wallet Spending Caps
  articleas classification.technologies2026-10-27
• The Impact of AI on CVEs: Industry Challenges
  articleas classification.technologies2026-10-27
• AI Agents Found a Way Into Anthropic's Business Systems in Under 12 Hours
  articleas classification.technologies2026-10-26
• Stolen AI Reasoning Could Help China Build Cheaper Rivals
  articleas classification.technologies2026-10-26
• Sweden's Government Offices Block ChatGPT and Claude, Keep Microsoft Copilot
  articleas affected products2026-10-24It is written here as Claude (blocked on Sweden's Government Offices staff computers from 26 October, Monday).

  blocked on Sweden's Government Offices staff computers from 26 October, Monday

• Crypto's Two Answers to AI Bug Hunters
  articleas classification.technologies2026-10-23
• Yash Patil (@yvshpvtil) on X
  threadas classification.technologies2026-10-23
• LLMs are making formal software verification feasible at a much larger scale
  articleas classification.technologies2026-10-22
• There isn't an easy exploit for this PHP vulnerability
  articleas classification.technologies2026-10-21
• ‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake Targets
  articleas classification.technologies2026-10-21
• Memory Bugs Account for Most of Chrome’s 353 New Security Fixes
  articleas tools2026-10-21It is written here as Claude (Anthropic): used to assist Xinyang Ge (Anthropic) in finding Chrome vulnerabilities.

  Anthropic

• Using Claude to reduce the attack surface of code
  articleas classification.technologies2026-10-21
• Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
  paperas classification.technologies2026-10-20
• ‘Wow, it’s a real discovery’: Claude cracks a 25-year NSA number mystery
  articleas classification.technologies2026-10-17
• Hackers Jailbreak iPhone 18 Pro on Stage, and It Survives a Reboot
  articleas classification.technologies2026-10-16
• Claude reveals ECDSA curve origins
  writeupas classification.technologies2026-10-16
• India's Cyber Agency Says AI Agents Read Confidential Business Records Without Authorization
  articleas classification.technologies2026-10-16
• In Other News: ICS-Sniper Attack, Hacking XWorm Malware Operators, $250k Chrome Exploit
  articleas classification.technologies2026-10-16
• Hidden Text, a Fake Mailbox: How Researchers Got Rogue AI Agents to Talk
  articleas classification.technologies2026-10-15
• Anthropic Gives Open Source Maintainers a Fast Track to Mythos Vulnerability Findings
  articleas classification.technologies2026-10-15
• Godfather of AI and 400 Scientists Want AI Models Cut Off From the Internet
  articleas classification.technologies2026-10-14
• Crossing the Threshold: How OpenAI and Anthropic Approach Autonomy and Safety in Financial Agents
  articleas classification.technologies2026-10-14
• Victor (@VMG_CU) on X
  threadas affected products2026-10-14It is written here as Claude (free credits lure).

  free credits lure

• INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
  paperas classification.technologies2026-10-14
• Chrome, Firefox Updates Patch 114 Flaws as Mozilla Unveils Firefox Enterprise
  articleas classification.technologies2026-10-14
• Anthropic says AI distillation attack defenses cut Claude extraction by 90% to 99%
  articleas affected products2026-10-13It is written here as Claude (reasoning transcripts targeted for extraction).

  reasoning transcripts targeted for extraction

• Strengthening our defenses against distillation attacks
  articleas classification.technologies2026-10-13
• Just say no to OpenAI and Anthropic
  articleas classification.technologies2026-10-12
• Context Engineering for Application Security | Endor Labs
  articleas classification.technologies2026-10-12
• Strengthening our defenses against distillation attacks
  articleas classification.technologies2026-10-12
• Hackers abuse Google Ads, Bing redirects to push Claude ClickFix attacks
  articleas classification.technologies2026-10-10
• Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments
  paperas classification.technologies2026-10-10
• In Other News: AI Used in Korean Bank Breaches, Poem-Guided Botnet, Empire Admin Gets 40 Years
  articleas tools2026-10-09

  AI assistant; memory files found by CrowdStrike during analysis of attack infrastructure

• Anthropic Fast-Tracks AI Bug Reports to OSS Maintainers, Taps 11 Firms for OT Security
  articleas tools2026-10-09It is written here as Claude (frontier models).

  used by CIDP partners to help fix OT vulnerabilities and assist customers in doing the same

• ORCAGen: Orchestrating Context-Aware Malware Deception with RAG-Guided Generative AI
  paperas classification.technologies2026-10-08
• Anthropic Introduces 3-Tier Cyber Verification Program for AI Access
  articleas classification.technologies2026-10-07
• Expanding the Cyber Verification Program
  articleas classification.technologies2026-10-06
• Top AI agent security resources — October 2026
  articleas classification.technologies2026-10-04
• Companies Push AI Use But Skip Training and Official Policy
  articleas affected products2026-10-02

  Used via company-managed/enterprise accounts or personal accounts by surveyed knowledge workers; personal accounts lack enterprise data protections

• China-aligned TA419 impersonates Anthropic employee, ex-White House official to phish AI policy experts
  articleas classification.technologies2026-10-02
• Identity Management for Agentic AI [pdf] (2025)
  paperas affected products2026-10-01

  large foundation model-based agentic system discussed as example of AI agent requiring new auth/authz models

• Huntress Tragic Quadrant: Top Cyber Threats Wrecking Businesses
  articleas affected products2026-10-01It is written here as Claude (claude.ai).

  Trusted AI platform domain abused to host a malicious Claude Artifact impersonating Claude Desktop, used in the FakeAgent campaign

• The Fine Art of Frustrating the Adversary
  articleas tools2026-10-01

  Anthropic AI agent referenced in a report describing four real-world incidents in evaluation environments with unintended internet access.

• Gemini 4 Is Here, and Google’s Flagship Tops All Other AI Models on Cybersecurity
  articleas classification.technologies2026-09-30
• Quoting Anthropic Frontier Red Team
  articleas classification.technologies2026-09-29
• A Privacy Analysis of Web and Mobile Conversational AI Agents [pdf]
  paperas affected products2026-09-29It is written here as Claude (web: claude.ai, Android: com.anthropic.claude).

  Tranco rank 617, >10M Play Store installs

• Implementing and Evaluating a Basic Per-Action Monitor for Safer Evals
  writeupas classification.technologies2026-09-27
• Understanding the Impact of LLM Watermarking on AI Agent Behavior
  writeupas classification.technologies2026-09-26
• ToolLeak: Tool-Invocation Attacks on Coding Agents
  paperas classification.technologies2026-09-21
• How AI Is Reshaping Crypto Security, with Michael Coates
  articleas tools2026-09-19

  AI model reportedly used by a Chinese state group to run an autonomous espionage campaign, per Anthropic's November 2025 disclosure

• Outrider Recon
  repoas classification.technologies2026-09-19
• Hackers breach OpenAI using Claude tools, gaining access to employee accounts and the company
  articleas classification.technologies2026-09-18
• Auditing in the age of (good enough) AI
  writeupas tools2026-09-18

  AI agent used for planning and development of the LSP server, decompiler, static analysis engine, MASM-to-Lean translator, and CLIs

• [tl;dr sec] #346 - Can AI Do Novel Security Research?, Anthropic's Threat Intel Report, How Cloudflare Enforces Engineering Standards
  articleas classification.technologies2026-09-17
• Maskit
  repoas affected products2026-09-15It is written here as Claude (claude.ai).

  Web-based AI service; Maskit browser extension provides tested/built-in authorization, attachments (.docx/.xlsx/.pptx) supported

• RepoGuardBench
  repoas affected products2026-09-13
• Anthropic Identifies Biased Reasoning and Recklessness as Drivers of Claude’s PyPI Attack
  articleas classification.technologies2026-09-10
• A “proof” of Fermat’s Last Theorem that fits the margin
  writeupas classification.technologies2026-09-09
• GTIG AI Threat Tracker: From Prompting to Autonomy – The Evolution of Adversarial AI
  articleas tools2026-09-08

  LLM queried by threat actors and a target of account purchases

• How Endor Labs AI SAST Learns What Matters to Your Organization | Blog | Endor Labs
  articleas classification.technologies2026-09-07
• The AI Attack Surface: How Threat Actors Abuse Trusted AI Platforms
  writeupas classification.technologies2026-08-27
• Could OpenClaw have actually hacked that Australian gym? We decided to test it.
  writeupas classification.technologies2026-08-25
• How Claude Watermarks AI-Generated Text
  talkas affected products2026-08-22It is written here as Claude (Anthropic LLM models).

  Text outputs are watermarked; example model named is 'Claude Opus 4.8' (used as an illustrative example in the video)

• Deep Eye
  repoas tools2026-08-22

  AI provider used for intelligent payload generation

• Putting models to the secure coding test: Plan vs default mode
  articleas tools2026-08-19

  Coding agent used to run Sonnet 5 in manual (default) and plan mode

• How to Spot and Stop Rogue Device Joins
  writeupas tools2026-08-18

  Asked by Wiz researchers to analyze unusual User-Agent strings observed in device-registration and sign-in activity to identify characteristics consistent with AI-generated tooling

• MacSync Stealer: How a Google Search for Claude Led to a macOS Infostealer
  writeupas classification.technologies2026-08-17
• Claude-Powered Agent Exploits Australian Gym API
  articleas tools2026-08-10

  Anthropic AI model powering the OpenClaw agent

• Lessons from the hacks
  articleas affected products2026-08-09It is written here as Claude (Anthropic).

  Contrasted with OpenAI models as less persistent/'lazy' and having a stronger 'user world model', described as feeling less dangerous.

• 77 "Evil Twin" Open VSX Extensions
  articleas affected products2026-08-08It is written here as Claude (AI coding agent config).

  Mini Shai-Hulud malware injects Claude configuration files (.claude) into repositories for persistence and to reach AI coding agents

• Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts
  articleas classification.technologies2026-08-06
• Anthropic Incident: An AI Agent Published a Malicious Package to PyPI and 15 Real Systems Ran It
  articleas classification.technologies2026-08-03
• System Prompts Leaks
  repoas classification.technologies2026-08-03
• asgeirtj/system_prompts_leaks
  repoas classification.technologies2026-08-03
• UseOSINT/Skills
  repoas classification.technologies2026-08-02
• Socket: Claude Breached 3 Companies and Uploaded Malware to PyPI During Anthropic's Security Tests
  articleas classification.technologies2026-08-01
• Top Agentic AI security resources — August 2026
  articleas classification.technologies2026-07-31
• Beetle
  repoas tools2026-07-31

  Optional AI provider for Beetle's AI Assistant/AI Actions

• elementalsouls/Claude-OSINT
  repoas classification.technologies2026-07-31
• Shift Left and Hunt Deep: Announcing Automated Exposure Discovery Engines for macOS XPC and Oracle Cloud IAM
  articleas tools2026-07-30

  LLM used by FAInd my XPC's AI agent to reverse-engineer daemon exposed methods, argument signatures, protocols, and connection-acceptance rules, and to verify exploit outcomes

• Slopsquatting: When AI Agents Hallucinate Malicious Packages | Blog | Endor Labs
  articleas classification.technologies2026-07-29
• Reverse Engineering the Six Stages of MacSync Stealer and RAT
  writeupas affected products2026-07-29It is written here as Claude (claude.ai).

  Abused via public 'share' conversation feature (claude.ai/share/<id>) to host a weaponised fake Apple Support install guide

• Visa Vulnerability Agentic Harness (VVAH)
  repoas classification.technologies2026-07-29
• Using Claude’s Security Review Skill in Claude Code
  articleas classification.technologies2026-07-29
• How Anthropic Secures its AI-Native SDLC
  articleas classification.technologies2026-07-26
• Socket: New Study Identifies 53 Slopsquatting Targets Across 5 Frontier LLMs
  articleas classification.technologies2026-07-23
• Inside FakeAgent: How a Claude Desktop Malvertising Campaign Hit 29 Organizations with SectopRAT
  writeupas classification.technologies2026-07-22
• AI Security Briefing
  articleas classification.technologies2026-07-18
• AI Security Briefing
  articleas classification.technologies2026-07-18
• AI Security Briefing
  writeupas classification.technologies2026-07-18
• AI Security Briefing
  writeupas tools2026-07-18

  AI agent option backing GitHub Agentic Workflows

• VulnHunter (Capital One)
  repoas classification.technologies2026-07-18
• deep scan tuto
  writeupas tools2026-07-14It is written here as Claude (Fable 5 and Opus 4.8).

  LLM agent models used to drive the MCP-based triage/remediation skills

• Sonnet 5 vs Fable 5: reliable versus security-forward, not better versus worse | Blog | Endor Labs
  writeupas classification.technologies2026-07-09
• Claude Sonnet 5 with Claude Code: strong on function, average on security, and unusually honest | Blog | Endor Labs
  writeupas classification.technologies2026-07-09
• Benchmarking Endor Labs AI SAST: 2.6x more real vulnerabilities found than frontier models | Blog | Endor Labs
  articleas classification.technologies2026-07-06
• api-relay-audit
  repoas classification.technologies2026-07-04
• FOSSA: Underappreciated OSS License Compliance Risk from AI Coding Tools
  articleas affected products2026-07-03

  AI coding assistant discussed as part of the category introducing OSS license compliance risk

• Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?
  writeupas classification.technologies2026-06-29
• What nearly 10,000 developer environments reveal about agentic development risk
  articleas affected products2026-06-23

  AI coding environment; developers found running multiple such environments simultaneously

• Teycir/SkillsGuard
  repoas classification.technologies2026-06-21
• Armur-Ai/Pentest-Swarm-AI
  repoas tools2026-06-21

  Supported LLM provider for the swarm orchestrator; prompt caching used to cut cost/latency

• The OpenSourceMalware Show #9
  talkas classification.technologies2026-06-18
• When a Government Pulls an AI Model: What the Fable 5 and Mythos 5 Suspension Means for Security Teams
  articleas classification.technologies2026-06-14
• Hacking Google with A.I. for $500,000
  writeupas tools2026-06-11

  AI used as the automated fuzzing/pentesting agent via MCP tools to probe Google APIs and report vulnerabilities

• Defending Code Reference Harness
  repoas classification.technologies2026-06-05
• Claude.ai Prompt Injection Vulnerability | Oasis Security
  writeupas classification.technologies2026-06-03
• Datadog AI-Native SAST
  articleas classification.technologies2026-05-31
• Hard Truths: You've Built a Security Stack. Have You Built a False Sense of Security? | Tanya Janca
  videoas technologies2026-05-27
• Project Glasswing: Initial Update (Anthropic)
  articleas classification.technologies2026-05-27
• AI-Assisted Vulnerability Discovery
  articleas classification.technologies2026-05-15
• Security Architecture of GitHub Agentic Workflows
  articleas classification.technologies2026-05-13
• DeepSec
  repoas classification.technologies2026-05-13
• Claude Code Auto Mode
  articleas classification.technologies2026-05-13
• PromptZero
  repoas classification.technologies2026-05-12
• knostic/OpenAnt
  repoas classification.technologies2026-05-12
• Alice and Bob Learn Secure Coding: Chapter 2
  videoas technologies2026-05-11
• claude-code-security-review
  repoas classification.technologies2026-05-10
• Negative Days in LLM Workflows
  writeupas classification.technologies2026-05-05
• requie/LLMSecurityGuide
  repoas affected products2026-05-05

  Conversational AI LLM cited as example

• Claude Cowork Exfiltrates Files
  writeupas classification.technologies2026-01-27
• Agent Capability Is a System Design Problem: Lessons From a 90% Improvement on CyberGym | depthfirst
  articleas classification.technologies2025-11-24
• rikugan: LLM reverse-engineering agent for IDA Pro and Binary Ninja
  repoas classification.technologies
• Rekt - News or Hype?
  articleas tools

  Anthropic model that traced the NIST curve seeds; Filippo Valsorda reimplemented the method and verified it; also assisted with drafting this article

• SnailSploit/Claude-Red
  repoas classification.technologies
• Claude Code Complete Guide: Hooks, Agents, MCP Tools & Professional Development
  courseas classification.technologies
• AI Agents Aren’t Waiting for Global Safety Rules
  articleas classification.technologies
• Security in the LLM Age - Greg Kroah-Hartman
  videoas technologies
• Google, Anthropic, and OpenAI Unveil Cyber AI Models, Safeguards, and Access Programs
  articleas classification.technologies
• AI Recommendation Poisoning: How
  articleas affected products

  supports deep-linked queries via URL parameters (claude.ai/new?q=...) exploited by the attack

• Distributed Attacks in Persistent-State AI Control
  paperas classification.technologies
• From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
  paperas affected products

  LLM backbone shown susceptible to guardrail reasoning-length DoS attack via payload transfer

• AI-Assisted HTTP Terminator Finds Novel HTTP Desync Techniques and Apache Zero-Day
  articleas classification.technologies
• SnailSploit/Claude-Red
  repoas classification.technologies
• Lonkero — Rust web vulnerability scanner (v3.7, AI agent mode)
  repoas classification.technologies
• Detecting and countering misuse of AI: September 2026
  articleas affected productsIt is written here as Claude (Haiku, Sonnet, Opus models).

  Misused by threat actors across cyber operations described in report

• 0x4m4/hexstrike-ai
  repoas classification.technologies
• What happened after 2,000 people tried to hack my AI assistant — Fernando Irarrázaval
  writeupas classification.technologies
• Sockpuppeting: How a Single Line Can Bypass LLM Safety Guardrails | TrendAI (US)
  writeupas classification.technologies
• capitalone/VulnHunter
  repoas classification.technologies
• Dev Machine Guard Now Supports Windows - StepSecurity
  articleas affected products

  AI coding agent, scanned for on developer machines

• Dev Machine Guard Now Supports Linux - StepSecurity
  articleas classification.technologies

In every workspace you can read 307