Agentic security review for Rust. An autonomous recon → find → grade → find→fuzz → report → patch loop for the bugs that actually bite Rust: memory-safety in unsafe/FFI, panic-DoS from untrusted input, deserialization trust (an integrity check is not a bounds check), and Send/Sync + panic-safety soundness. Static analysis drives the dynamic stage — the threat model routes which sanitizer, fuzz rung, and vote budget each finding gets. Detectors: Miri (undefined behavior), AddressSanitizer, panic/abort, hang-timeout, and cargo-fuzz for execution-verified reproduction. Enjoy
The full story
This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.
