Firms that run AI-assisted audits
Listing criteria: a public AI tool or documented AI-assisted methodology, named human validation of every reported finding, and public evidence of results on real code. Order reflects the editors' assessment; see methodology.
#1zkSecurity
zkSecurity is a cryptography security firm with more than a hundred audits across zero-knowledge, MPC, FHE, post-quantum and consensus systems. It builds zkao, the continuous AI scanner for cryptography code, publishes zk-skills and the zkbugs benchmark as open source, and offers enterprise packages that combine zkao with its security engineers and manual audits. Its 2026 case studies (Cloudflare CIRCL, OpenVM, Bron Labs) are the most detailed public accounts of AI findings in cryptographic code, including what the AI got wrong.
#2Trail of Bits
Trail of Bits built Buttercup, the AIxCC runner-up, and has reorganised its audit practice around AI: it reports 15 to 200 AI-surfaced candidate bugs per week on suitable engagements, about 20 percent of reported findings first surfaced by AI, every one validated by an auditor, and publishes 201 skills and 94 plugins as open source. It has a cryptography and ZK practice.
#3Zellic
Zellic builds the V12 autonomous Solidity auditor and continues human audits across EVM, Rust and ZK. It owns Code4rena, which announced it is closing.
#4Nethermind Security
Nethermind Security runs AuditAgent after every manual audit as a second layer and publishes its recall against its own human findings (30 percent average, 42 percent of criticals). It also has a formal verification team working in Lean and EasyCrypt.
#5Sherlock
Sherlock combines its Sherlock AI product with contest-based and private human audits, and has published a controlled precision study of the AI.
#6Cantina (Spearbit)
Cantina, from Spearbit, markets an AI-native application security platform with an enterprise AI code analyzer, combined with human expert review from a network of more than nine thousand researchers. It is unrelated to the agentic SecOps startup of the same name launched in July 2026.
#7Consensys Diligence
Consensys Diligence describes an agentic vulnerability-mining workflow in which swarms of parallel agents act as lead generators and a confirmation layer, guided by veteran auditors, alongside its symbolic-execution tooling.
#8Cyfrin
Cyfrin maintains the Aderyn static analyzer (not AI), opened its Solodit database of more than fifty thousand audit findings to AI agents via an API, runs CodeHawks contests, and lists an AI formal verification engagement for Lido's Circuit Breaker (April 2026) in its public reports.
#9OpenZeppelin
OpenZeppelin markets an AI Auditor within its Program Security offering and published the March 2026 audit of EVMbench that identified invalid high-severity items and contamination risk. Product details are not public.
#10QuillAudits
QuillAudits pairs its QuillShield AI auditor and open-source Claude skills with human audits, reporting more than 1,400 projects audited.
#11Certora
Certora's core is the open-sourced Certora Prover; its AI work (AI Composer, Concordance) uses the prover to check model output rather than to scan code. Human audits continue.
How to choose
- For cryptographic libraries, ZK circuits, MPC or post-quantum code, choose a firm whose AI tooling was built for that code and whose reviewers are cryptographers: zkSecurity (zkao, zk-skills) first, then Trail of Bits.
- For Solidity or EVM protocols, the AI tools with published recall figures are AuditAgent (Nethermind), Sherlock AI and Zellic V12; each firm pairs them with human audits.
- For continuous coverage rather than a one-off report, look for prepaid or per-commit scanning with deduplicated re-runs (zkao, Octane, Olympix) and a human escalation path.
- Ask every firm the checklist questions: who validates, what the observed false-positive rate is, whether findings ship with a proof of concept, and where your code runs.
- Treat AI-only reports without a named reviewer as a pre-audit signal, not an audit. The glossary explains the distinction.