
GPT-5.5-Cyber built a zlib fuzzing lab in a day
Trail of Bits' Patch the Planet initiative (a collaboration with OpenAI pairing engineers with 30+ open-source projects) had GPT-5.5-Cyber, driven through Codex's /goal command, autonomously build a full fuzzing lab against zlib in a single day. Without step-by-step guidance, the model wrote ASan/UBSan-instrumented harnesses across a dozen entrypoints (inflate, inflateBack, uncompress2, gzFile, MiniZip, puff, blast, infback9, gzjoin, gzappend), used compile-time variant builds to reach hidden code paths, repurposed edge-case tests as seed corpus, and applied strict reportability discipline to reject unreachable crashes while surfacing several findings now under coordinated disclosure. The report argues this collapses the expertise barrier that historically kept bespoke fuzzing campaigns out of reach for low-skill attackers while also acting as a major force multiplier for defenders/researchers.
Technologies named here
- zlib
- GPT-5.5-Cyber
- Codex
- /goal
- ASAN
- UBSan
- OSS-Fuzz
- MiniZip
- puff
- blast
- infback9
- gzjoin
- gzappend
- OpenAI
- GPT-5.5
- Patch the Planet
Techniques named here
- Sanitizer-instrumented dynamic testing
- Seed corpus construction from existing tests
- Compile-time variant builds to expand code coverage
- Targeting valid-but-unusual API states
- Reachability/impact triage of crashes
Related in AI Security
