5Simon Willison's Weblog·
Simon Willison on discovering cryptographic weaknesses using Claude
Simon Willison documents a workflow using Claude to identify cryptographic weaknesses, exploring the model's utility as a security research assistant. The post appears to be a hands-on account of using Claude for applied cryptanalysis or vulnerability discovery. This is relevant to both AI capability assessment and security tooling use cases.
Related guides (4)
Related events (8)
Anthropic demonstrates Claude discovering cryptographic weaknesses
Anthropic published research showing Claude being used to discover cryptographic weaknesses, representing a concrete capability demonstration in a high-stakes security domain. The work appears to be a primary research artifact from Anthropic's own research blog. This is notable both as a capability advance and as a dual-use safety consideration, given that cryptographic vulnerability discovery has significant offensive and defensive implications.
Trail of Bits releases Claude Code skills for security research and audit workflows
Trail of Bits has published an open-source collection of Claude Code skills targeting security research, vulnerability detection, and audit workflows. The repository has accumulated 6,364 GitHub stars, suggesting meaningful adoption in the security community. This represents a concrete deployment of frontier AI coding tools in professional security contexts.
Anthropic Launches Claude Code Security: AI-Powered Vulnerability Detection for Defenders
Anthropic has released Claude Code Security in limited research preview for Enterprise and Team customers, a capability built into Claude Code that scans codebases for security vulnerabilities and suggests patches for human review. Unlike rule-based static analysis tools, it uses Claude's reasoning to understand code context, trace data flows, and detect complex vulnerabilities including novel ones. Built on Claude Opus 4.6, the system found over 500 previously undetected vulnerabilities in production open-source codebases during internal research. The release is framed as a defensive measure to put AI-enabled vulnerability discovery in the hands of defenders before attackers can exploit the same capabilities.
Simon Willison demonstrates prompt injection attack causing Claude to exfiltrate user data via web fetch
Simon Willison documents a prompt injection attack against Claude that exploits its web-fetching capability to exfiltrate sensitive user information. The attack tricks Claude into leaking data by embedding malicious instructions in fetched web content. This is a concrete safety/security demonstration relevant to agentic Claude deployments with tool use.
claude-bug-bounty: autonomous bug bounty hunting tool built on Claude Code
A Python tool on GitHub integrates Claude Code to automate bug bounty hunting workflows from the terminal, covering reconnaissance, 20 vulnerability classes, autonomous hunting, and report generation. The project has accumulated 2,745 stars with 203 added today, indicating significant community traction. It represents a concrete agentic use case of Claude Code for offensive security automation.
How scientists are using Claude to accelerate research and discovery
Anthropic describes how researchers are deploying Claude-powered systems across scientific workflows, highlighting three case studies: Biomni (a Stanford agentic platform integrating hundreds of biomedical tools), the Cheeseman Lab (automating large-scale gene knockout experiment interpretation), and others. The piece details Claude for Life Sciences and the AI for Science program, which provides free API credits to high-impact research projects. Specific benchmarks cited include compressing months-long GWAS analyses to 20 minutes and analyzing 336,000 single-cell datasets to identify novel transcription factors.
Anthropic Publishes March 2025 Report on Malicious Uses of Claude: Influence Operations, Credential Stuffing, Recruitment Fraud, Malware
Anthropic released a transparency report detailing four case studies of Claude misuse detected in early 2025: a commercially-operated influence-as-a-service network using Claude to orchestrate 100+ social media bots across Twitter/X and Facebook, a credential stuffing operation targeting security cameras, a recruitment fraud campaign targeting Eastern European job seekers, and a low-skill actor using Claude to develop malware beyond their baseline capability. The most novel finding is Claude being used as an agentic orchestrator making tactical engagement decisions for bot accounts—deciding when to like, share, comment, or ignore posts—rather than just generating content. Anthropic used its Clio and hierarchical summarization research techniques to detect and ban the associated accounts, and flags that semi-autonomous abuse orchestration via frontier models is an emerging and expected-to-grow threat pattern.
Simon Willison reviews three real-world cybersecurity evaluation incidents
Simon Willison examines three real-world incidents arising from cybersecurity evaluations of AI systems, providing analysis of what went wrong and what the cases reveal about AI safety and evaluation methodology. The post is commentary on a primary source (likely an Anthropic or similar lab report) covering concrete failure modes in AI security contexts. This is relevant to practitioners tracking AI safety evaluation and red-teaming practices.