← → Print all
03 — Auditing · Assurance guide

LLM-assisted review

Emerging tooling

In one paragraph

LLM-assisted review: Emerging tooling. Layer: Circuit / libraries. Characteristic finds: Sustained attention over large cryptographic library surfaces (evidence so far: a single self-reported finding). Blind to: Unknown and unmeasurable; false negatives are invisible. Coverage claim: None. Cost profile: Low per run; expert triage is the real cost. Choose it when: A supplementary sweep alongside manual review and deterministic tooling, especially over large cryptographic library surfaces. Not a substitute for any other category.

By MarketComp Updated v1.3 About the authors Changelog
Layer
Circuit / libraries
Characteristic finds
Sustained attention over large cryptographic library surfaces (evidence so far: a single self-reported finding)
Blind to
Unknown and unmeasurable; false negatives are invisible
Coverage claim
None
Cost profile
Low per run; expert triage is the real cost
Assurance matrix · see the row in context

What it is

Automated review pipelines built on large language models with domain-specific context engineering, run over circuit and cryptographic library code. The category has moved from speculative to evidenced: a missing subfield membership check in an optimised pairing routine was found this way, assigned a CVE, and fixed upstream. Disclosure: that finding is the work of this document's maintainer, and it is a single self-reported result — weight it accordingly against the peer-reviewed evidence behind the other categories here.

Strengths and tradeoffs

Strengths
  • Sustains attention over large codebases where human reviewers fatigue
  • Not restricted to a modelled bug class the way SMT and lint tooling is
  • Cheap enough to re-run on every change
Tradeoffs
  • Results depend heavily on pipeline design; naive prompting fails where context-engineered flows succeed
  • No soundness or coverage guarantee; false negatives are invisible
  • False positives consume expert triage time, which is the scarce resource
  • Leading pipelines are proprietary and not independently reproducible, so published claims cannot be checked
  • Must not be represented to third parties as equivalent to human or formal review

Choose it whenA supplementary sweep alongside manual review and deterministic tooling, especially over large cryptographic library surfaces. Not a substitute for any other category.

Maintained implementations

Not recorded for this entry.

Maturity: Emerging; one CVE-assigned production finding · License: Varies; mostly proprietary · blog.zksecurity.xyz ↗

How to decide
Other assurance guides in §03
ZK security consultanciesManual circuit and constraint reviewAutomated underconstraint detectionFormal verification of ZK circuitsDifferential and fuzz testingCryptographic review of the protocol and proof systemVerifier and integration reviewAudit contestsBug bounties

Sources cited on this page · 1

  1. Missing subfield membership check in OpenVM pairing — CVE-2026-46669disclosure

All 48 sources for §03 are listed on the section page →

Cite this page 
MarketComp (2026). LLM-assisted review. The ZK Field Manual (Version 1.3). MarketComp. https://zkpick.com/audit/llm-assisted-review/
@misc{zkfieldmanual-llm-assisted-review,
  title        = {LLM-assisted review — The ZK Field Manual},
  author       = {MarketComp},
  year         = {2026},
  version      = {1.3},
  howpublished = {\url{https://zkpick.com/audit/llm-assisted-review/}},
  note         = {Accessed: YYYY-MM-DD}
}