Microsoft FORGE Lab uses agentic AI tools to find memory-safety bugs in Rust core libs
jedisct1 · x · 2026-11-10
Microsoft's FORGE Lab reported multiple memory-safety issues in Rust's core and std libraries — including cases where code written entirely in safe Rust can trigger undefined behavior.
- The research identifies three recurring patterns of misplaced trust in unsafe code: trusting code not to panic, trusting user-provided implementations to be correct, and trusting the underlying system
- Issues affect iterator cloning, string replacement, and OS interactions
- Using Hyenas (a research version of codename MDASH), the team combined AI-assisted vulnerability discovery with manual investigation, reproduced the bugs, assessed impact, and worked with Rust maintainers on fixes
More from coding & agent
- Author shares his actual orchestrator prompt: sliced plans plus skeptical sub-agent reviews — thatroblennon · 2026-11-10
- Community-built Claude skill prunes useless UI copy, works surprisingly well with Opus — floguo · 2026-11-10
- Two 'fresh eye review' prompts catch AI coding mistakes after generation — doodlestein · 2026-11-10
- InstructGPT co-author's Jev harness PDF promises 200x faster, 400x cheaper coding agents — Redo · 2026-11-10
- Three coding-agent security patches ship this week: Mistral Vibe, Jan, DeepSeek Harness — alvelda · 2026-11-10
- Dev rewrote Node app in Go, asks why developer-friendly languages matter when AI writes code — rakyll · 2026-11-10