{"data":{"id":"5701aa79-ef97-4ec6-b1c7-13a2678c4f24","title":"Ulysses: A Security Harness For Synthesizing Verifiable Web Exploits","summary":"Ulysses is a multi-agent security harness that turns candidate web application vulnerability findings into verified Proofs of Exploitability by testing exploit hypotheses against independently observed execution effects. Evaluated on WebExploitGym, a benchmark of exploitable instances from 25 real-world web applications across 5 languages and 7 frameworks, it produced verified proofs for 10 of 25 real-world advisories and discovered 4 new proofs of exploitability never previously reported.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.31831v1","publishedAt":"2026-10-22T19:11:08.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-22T19:11:08.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":null,"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":"preprint","atlasIds":null}}