Top 200 ReposEXPLORER
Browse agents, categories and pages

Security Research

Auditing code and systems for vulnerabilities, with human verification of every finding.

3 use cases · Filters

Specific jobs

Agents

Use Cases

Reported by source

Hunt for variants of fixed bugs with an LLM agent, as Google's Big Sleep did in SQLite

Google's Big Sleep agent started from recent SQLite fixes, looked for related unfixed bugs and found an exploitable stack buffer underflow before it reached an official release.

projectzero.google · 1 Nov 2024
Planned, not done

Let an agent decompile and annotate a binary in Ghidra through GhidraMCP

GhidraMCP exposes Ghidra's decompiler and renaming tools over MCP, so an agent such as Claude Code can list functions, read decompiled code and propose clearer names.

github.comNationalSecurityAgency/ghidra
Reported by source

Audit kernel code for use-after-free bugs with a reasoning model

Sean Heelan benchmarked OpenAI o3 on a known ksmbd bug, then ran it across the SMB handlers, where it surfaced a new Linux kernel vulnerability, CVE-2025-37899.

sean.heelan.io · 22 May 2025