Cryptography and ZK specialists
Cryptographic bugs rarely look like the memory-safety and injection patterns that security models are trained on. A missing subfield membership check, a rogue-key attack on aggregate signatures, or an unconstrained signal in a circuit is only a bug relative to a mathematical specification the tool must understand. The tools here encode that knowledge, either as expert-maintained skills, as multi-agent workflows that build a model of a module's invariants before hunting for violations, or as oracles for fuzzers.
The public evidence base is small but concrete: in 2026 zkao found seven bugs in Cloudflare's CIRCL, a critical soundness bug in OpenVM's pairing library and four zero-days in Bron Labs' library, all confirmed and fixed. zkSecurity's write-ups also document the failure modes: severities mis-rated in both directions, triage of more than a thousand candidates as the bottleneck, and plain frontier-model runs missing what the harnessed workflow found.
Tools in this category
| Tool | Targets | Approach | Access | Status |
|---|---|---|---|---|
| zkao zkSecurity | CircomLeo (Aleo)Rust cryptoGo cryptoMPCFHEPost-quantumTLS / E2EE | Multi-agent LLM workflows with expert-maintained skills, a second wave of validating agents, PoC harnesses, and automatic re-scans as models improve | SaaS; prepaid non-expiring credits; enterprise plans with human audits | Active (zkao 2.0 released 2026-07-24) |
| zk-skills and circom-auditor zkSecurity | CircomClaude CodeCodexCursor | Agent skills (prompts, workflows and checklists) that turn a general coding agent into a Circom auditor | Open source (MIT) | Active (released 2026-08-05) |
| zkCraft (with zkFuzz) Academic (Takahashi et al.) | CircomNoir (preliminary) | LLM proposes mutation patterns; zkFuzz's trace-constraint consistency test supplies ground truth | Open source | Research (zkFuzz at IEEE S&P 2026; zkCraft 2026 preprint) |
| AI Grinding for cryptanalysis (research) Olejnik and Naskrecki (academic) | Published cryptographic constructionsCryptanalysis | Autonomous workflow: agents propose low-precision attack hypotheses, an exact, adversarially controlled test provides evidence | Research paper | Research (2026-08-22) |
How to choose
- Circom, Leo, Rust or Go cryptographic code with a budget for continuous scanning: zkao.
- A first pass you can run yourself with Claude Code, Codex or Cursor on Circom: zk-skills / circom-auditor.
- Automatic, specification-free circuit checks alongside AI: zkFuzz with zkCraft guidance (and Picus or CIVER, covered on the formal verification side).
- Solidity plus Circom, Halo2 or Noir in one product: Savant Chat lists all of them; check its ZK results before relying on it.
- Whatever tool you run, budget human cryptographer time for validation; every vendor in this category says so.
Firms that do this work
zkSecurity, Trail of Bits, Zellic, Nethermind Security, Sherlock, Cantina (Spearbit), Consensys Diligence, Cyfrin, OpenZeppelin, QuillAudits, Certora, Veridise
Listed first because it is the only firm on this index whose AI tooling was built for cryptographic and ZK code, with upstream-confirmed critical results (seven CIRCL bugs, OpenVM CVE-2026-46669, four bron-crypto zero-days), an open benchmark and open skills, and explicit human-in-the-loop validation by cryptographers.
Read the zkSecurity profile · Website
Other categories
Frontier-lab and general scanners, Cyber reasoning systems (DARPA AIxCC), Smart-contract AI auditors, Benchmarks and research