<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  <title>QuillShield blog</title>
  <subtitle>Our EVMbench results, live bounty and contest results, an independent researcher's test and plain explainers on AI smart contract audits and pull request security.</subtitle>
  <id>https://shield.quillaudits.com/blog/</id>
  <link rel="alternate" type="text/html" href="https://shield.quillaudits.com/blog/"/>
  <link rel="self" type="application/atom+xml" href="https://shield.quillaudits.com/blog/feed.xml"/>
  <updated>2026-11-18T00:00:00Z</updated>
  <author>
    <name>The QuillShield team</name>
    <uri>https://shield.quillaudits.com/</uri>
  </author>
  <entry>
    <title>11 valid bugs in 20 live bounties and audit contests</title>
    <id>https://shield.quillaudits.com/blog/bug-bounty-and-contest-results/</id>
    <link rel="alternate" type="text/html" href="https://shield.quillaudits.com/blog/bug-bounty-and-contest-results/"/>
    <published>2026-11-18T00:00:00Z</published>
    <updated>2026-11-18T00:00:00Z</updated>
    <summary>11 findings judged valid, 4 filed as High, in 20 live Solidity bug bounties and audit contests from March to November 2026. 18 more are in judging.</summary>
  </entry>
  <entry>
    <title>QuillShield found a bug an independent researcher had ruled out</title>
    <id>https://shield.quillaudits.com/blog/independent-researcher-test/</id>
    <link rel="alternate" type="text/html" href="https://shield.quillaudits.com/blog/independent-researcher-test/"/>
    <published>2026-11-18T00:00:00Z</published>
    <updated>2026-11-18T00:00:00Z</updated>
    <summary>An independent researcher ran QuillShield on a live lending contract where he had ruled a bug out. It found an attack path past the safeguard that stopped him, and he reproduced it on a mainnet fork.</summary>
  </entry>
  <entry>
    <title>QuillShield found 98 of 117 known vulnerabilities on EVMbench</title>
    <id>https://shield.quillaudits.com/blog/evmbench-results/</id>
    <link rel="alternate" type="text/html" href="https://shield.quillaudits.com/blog/evmbench-results/"/>
    <published>2026-11-17T00:00:00Z</published>
    <updated>2026-11-17T00:00:00Z</updated>
    <summary>The QuillShield alpha found 98 of 117 known vulnerabilities on EVMbench (83.8%) in our own run on 8 July 2026. What EVMbench measures and how we ran it.</summary>
  </entry>
  <entry>
    <title>Can AI audit smart contracts? What the data shows</title>
    <id>https://shield.quillaudits.com/blog/can-ai-audit-smart-contracts/</id>
    <link rel="alternate" type="text/html" href="https://shield.quillaudits.com/blog/can-ai-audit-smart-contracts/"/>
    <published>2026-11-17T00:00:00Z</published>
    <updated>2026-11-17T00:00:00Z</updated>
    <summary>Yes. What AI finds on a public benchmark, how many of its findings auditors confirm, and how teams pair it with a manual audit.</summary>
  </entry>
  <entry>
    <title>AI audit vs manual audit: what each one is for</title>
    <id>https://shield.quillaudits.com/blog/ai-audit-vs-manual-audit/</id>
    <link rel="alternate" type="text/html" href="https://shield.quillaudits.com/blog/ai-audit-vs-manual-audit/"/>
    <published>2026-11-17T00:00:00Z</published>
    <updated>2026-11-17T00:00:00Z</updated>
    <summary>An AI audit reviews every change, and QuillShield tests findings with exploits where it can. A manual audit adds human judgment. How to use both.</summary>
  </entry>
  <entry>
    <title>How to evaluate an AI smart contract auditor</title>
    <id>https://shield.quillaudits.com/blog/evaluate-ai-smart-contract-auditor/</id>
    <link rel="alternate" type="text/html" href="https://shield.quillaudits.com/blog/evaluate-ai-smart-contract-auditor/"/>
    <published>2026-11-17T00:00:00Z</published>
    <updated>2026-11-17T00:00:00Z</updated>
    <summary>What to ask before you trust an AI auditor with unreleased code: benchmark results, findings that hold up, proof of concept, privacy and pull requests.</summary>
  </entry>
</feed>
