Anthropic used Claude to autonomously shrink attack surfaces across 25 major OSS codebases
chrisrohlf · x · 2026-10-21
Anthropic's security team tasked Claude with autonomously mapping and reducing the attack surface of 25 large, widely used open-source codebases, publishing their methodology and a data preview.
Key results:
- A significant reduction in OpenSSH's pre-authentication attack surface, now fixed in OpenSSH 10.6
- Over 500 findings where reachability could be reduced and configurations hardened to prevent security controls from being silently disabled
It's a notable example of handing tedious attack-surface hardening work to autonomous agents.
More from coding & agent
- Ornith-1.5-122B open-weights model claims 84.5% SWE-bench Verified, runs on a single DGX card — Teknium · 2026-10-21
- Running >1 autonomous agent: doc bloat, review bottlenecks, and why "don't edit" fails — menhguin · 2026-10-21
- LangChain expands agent redteaming beta: 34 hypotheses tested, 9 findings in one run — hwchase17 · 2026-10-21
- OvertChat: a polished self-hosted ChatGPT-style UI for local models, one-command install — anitamaxwynnn69 · 2026-10-21
- Smart Connections demo: Obsidian surfaces past decisions to reshape your plan — AINewsletter · 2026-10-21
- Ampersand v0.1 Ships via Agent API: Hosted Sessions, OpenAI-Client Compatible — gharik · 2026-10-21