Team self-disclosure of AI-generated Solidity
Uniswap (v2 + v3)'s assessment for RD-F-173 — scored green on the v1.7.0 rubric. The evidence below is the curator's reasoning for this score.
Evidence summary #
No public disclosure by Uniswap Labs of AI-generated Solidity in security-critical production contract paths. Uniswap/uniswap-ai is developer tooling, not AI-authored protocol code. Both versions designed 2020-2021, pre-LLM code generation era. Green.
Detail #
No blog post, tweet, or public documentation from Uniswap Labs or its contributors discloses AI-generated Solidity in V2 or V3 security-critical code paths. The existence of the uniswap-ai GitHub repo is sometimes cited as evidence of AI involvement — however, inspection shows it contains skills, plugins, and agents for coding agents building applications ON Uniswap, not AI-generated protocol code.
Sources #
- GitHubUniswap AI repo — tooling for developers, not AI-generated protocol codeUniswap/uniswap-airetrieved 2026-05-12
Methodology #
Determine whether the team has publicly disclosed (blog, tweet, docs) that AI-generated Solidity was used in security-critical paths.
See the full factor methodology and distribution across all protocols →