{"data":{"id":"f205dec9-ac3f-431a-9197-543fbf6efe80","title":"ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?","summary":"ProtoArena is a black-box benchmark of 80 cross-component protocol vulnerability-exploitation environments spanning 11 domains and 7 attack categories, primarily informed by published protocol-attack mechanisms. Five LLMs were evaluated, and Claude Opus 4.8 reached 48.8% success under L1 guidance and 12.5% under effect-directed black-box L3. Results show agents can achieve verifiable exploitation effects in some environments, but black-box success remains low and varies across domains.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.17837v1","publishedAt":"2026-10-13T06:56:32.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Claude Opus 4.8"],"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":"2026-10-13T06:56:32.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality","integrity","availability"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}