pip install poetry
poetry install

tasks/CVE-2026-33175/
├── meta.json           # GHSA ID, CWE, CVSS, repo URL, vulnerable and fixed SHAs
├── setup.sh            # Clones repo, checks out the vulnerable SHA, installs dependencies
├── run_tests.sh        # Injects test_security.py into the repo and runs pytest
├── test_security.py    # Security tests (xfail on vulnerable code, pass on the fix)
├── advisory.md         # Full GHSA advisory (richest prompt)
├── diagnose.md         # Behavioural description only — no file or function names
├── locate.md           # File and function only — no description of the flaw
└── Dockerfile          # Optional; only present when the task needs extra system deps

{
  "ghsa_id": "GHSA-xxxx-xxxx-xxxx",
  "cwe": ["CWE-287"],
  "cvss": 9.1,
  "repo": {
    "url": "https://github.com/org/project",
    "vulnerable_sha": "abc123^",
    "fixed_sha": "abc123"
  }
}

python build.py

# Build specific tasks only
python build.py --task CVE-2026-33175 CVE-2026-42561

# Skip rebuilding the base image
python build.py --skip-base

python validate.py

# Validate specific tasks only
python validate.py --task CVE-2026-33175 GHSA-r758-8hxw-4845

# Skip rebuilding images before validation
python validate.py --skip-build

python benchmark.py --model openai:gpt-5.5 poolside:laguna-m.1 --prompt-type advisory

results/{task-id}__{provider}:{model}__{prompt-type}.json

{
  "cve_id": "CVE-2026-33175",
  "model_id": "openai:gpt-5.5",
  "prompt_type": "advisory",
  "timestamp": "2026-05-01T12:00:00",
  "model_duration_s": 142.3,
  "test_duration_s": 8.1,
  "turns": [
    {
      "tool_calls_and_results": [...],
      "input_tokens": 12400,
      "output_tokens": 310
    }
  ],
  "tests": [
    {
      "kind": "security",
      "name": "test_email_verified",
      "outcome": "passed"
    }
  ]
}

python generate_charts.py

src/harness/
├── run.py                  # Entry point; parses args, wires components, calls BenchmarkRunner
├── client/
│   ├── factory.py          # Parses provider:model-id, returns the correct LLMClient
│   ├── _client.py          # Abstract LLMClient, ToolCall and LLMTurn dataclasses
│   ├── anthropic.py        # Anthropic SDK integration
│   └── oai.py              # OpenAI SDK integration (also used for Poolside)
├── agent/
│   ├── core.py             # Agentic loop: calls client, dispatches tool calls, threads messages
│   └── runner.py           # Wraps Agent, tracks timing and turn list
├── bench/
│   ├── runner.py           # Orchestrates setup → agent → security tests → regression tests
│   ├── result.py           # BenchmarkResult and TestResult dataclasses, JSON serialisation
│   └── repository.py       # Writes result files to disk
└── task/
    ├── tools.py             # Tool implementations: ListFiles, ReadFile, SearchInFiles,
    │                        #   EditFile, CreateFile, DeleteFile, RunPytest
    └── prompt_loader.py     # Reads advisory.md / diagnose.md / locate.md

@misc{gattipinheiro2026cvebench,
  author       = {Gatti Pinheiro, Giovanni},
  title        = {{CVE-Bench}: Benchmarking {LLM} Agents on Real-World Security Vulnerability Fixes},
  year         = {2026},
  howpublished = {\url{https://giovannigatti.github.io/cve-bench}},
  note         = {Code available at \url{https://github.com/GiovanniGatti/cve-bench}}
}