mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-16 19:59:26 +00:00
Marius CiepluchandClaude Opus 4.8
cf9f945992
Rebuild the quick-scan detection engine and ground-truth benchmarks to hit >=90% recall / <10% false positives for C/C++, Python, JavaScript, and Java. Engine (findings.py, preprocess.py): - Scope each PatternRule by language (fixes cross-language false positives such as the Python eval/exec rule firing on JS .exec()). - Add JavaScript/TypeScript rules (command exec, eval/Function, reflected XSS, SQLi, path traversal, SSRF, weak hash, deserialization); execFile/spawn-argv excluded as safe alternatives. - Add Java rules (Runtime exec, SQL string concatenation, weak hash, readObject) and a Groovy server-side template rule (yieldUnescaped of a bound variable). - Broaden C/C++ and Python coverage; precision guards for format strings and parameterised vs concatenated SQL; #-comment skipping; CWE in rationale. - Register .java/.groovy/.tpl source extensions. Benchmarks: - Add realistic corpora modeled on Damn Vulnerable C/C++, PyGoat/DVPWA, and NodeGoat, plus the real kiview/damn-vulnerable-spring-boot-app vendored verbatim (MIT, attribution in LICENSE/NOTICE.md). Each manifest carries complete, independently-labeled ground truth including genuinely hard-to-detect vulns (integer overflow, second-order SQLi, prototype pollution) so recall is measured honestly, plus safe-API files for precision. - Fix pre-existing smoke-manifest ground-truth errors (Python/JS line offsets, missing C/C++ strcpy entry, Java SQLi line). benchmark.py: - Fix sink matching to normalise the expected sink consistently so sinks with underscores (e.g. render_template_string) can match. Tests: - Add tests/test_detection_benchmarks.py enforcing the >=90% recall / <10% FP goal per language and overall. Measured: C/C++ 93.3%, Python 93.3%, JavaScript 92.3%, Java 100%; overall 93.6% recall, 0.0% false-positive rate. Co-Authored-By: Claude Opus 4.8 <[email protected]>
80 lines
3.2 KiB
Python
80 lines
3.2 KiB
Python
"""Detection-quality gate for the in-scope languages.
|
|
|
|
Runs quick-mode scans against the C/C++, Python, and JavaScript benchmark
|
|
corpora and asserts the project goal: at least 90% recall of known
|
|
vulnerabilities and under a 10% false-positive rate per language.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from openultrasast.benchmark import (
|
|
BenchmarkRun,
|
|
evaluate_benchmark,
|
|
load_benchmark_manifest,
|
|
resolve_benchmark_source,
|
|
)
|
|
from openultrasast.findings import quick_scan_findings
|
|
from openultrasast.mapping import analyze_entry_points, attach_reachability_hints
|
|
from openultrasast.preprocess import preprocess_repository
|
|
from openultrasast.rank import rank_targets
|
|
|
|
LANGUAGE_MANIFESTS = {
|
|
"c_cpp": ["c-cpp-smoke", "cpp-damn-vulnerable"],
|
|
"python": ["python-web-smoke", "python-vulnerable"],
|
|
"javascript": ["javascript-node-web-smoke", "javascript-vulnerable"],
|
|
"java": ["java-web-smoke", "java-spring-boot-vulnerable"],
|
|
}
|
|
|
|
RECALL_FLOOR = 0.90
|
|
FALSE_POSITIVE_CEILING = 0.10
|
|
|
|
|
|
def _quick_scan(target: Path): # type: ignore[no-untyped-def]
|
|
_, targets = preprocess_repository(target)
|
|
targets = attach_reachability_hints(targets, analyze_entry_points(target, targets))
|
|
rankings = rank_targets(targets)
|
|
return quick_scan_findings(target, targets, rankings)
|
|
|
|
|
|
def _language_metrics(manifest_names: list[str]) -> tuple[int, int, int, int]:
|
|
expected = matched = actual = false_positives = 0
|
|
for name in manifest_names:
|
|
manifest_path = Path(f"benchmarks/manifests/{name}.toml")
|
|
manifest = load_benchmark_manifest(manifest_path)
|
|
target = resolve_benchmark_source(manifest_path, manifest)
|
|
findings = _quick_scan(target)
|
|
run = BenchmarkRun(benchmark_run_id="gate", root=Path("/tmp/gate"), manifest=manifest)
|
|
result = evaluate_benchmark(run=run, mode="quick", findings=findings, scan_id=None, scan_run_dir=None)
|
|
metrics = result.metrics
|
|
expected += metrics.expected_findings_total
|
|
matched += metrics.matched_findings_total
|
|
actual += metrics.actual_findings_total
|
|
false_positives += metrics.false_positive_findings_total
|
|
return expected, matched, actual, false_positives
|
|
|
|
|
|
@pytest.mark.parametrize("language", sorted(LANGUAGE_MANIFESTS))
|
|
def test_language_meets_recall_and_false_positive_goal(language: str) -> None:
|
|
expected, matched, actual, false_positives = _language_metrics(LANGUAGE_MANIFESTS[language])
|
|
|
|
recall = matched / expected
|
|
false_positive_rate = false_positives / actual if actual else 0.0
|
|
|
|
assert recall >= RECALL_FLOOR, f"{language} recall {recall:.2%} below {RECALL_FLOOR:.0%} ({matched}/{expected})"
|
|
assert false_positive_rate < FALSE_POSITIVE_CEILING, (
|
|
f"{language} false-positive rate {false_positive_rate:.2%} at or above {FALSE_POSITIVE_CEILING:.0%} ({false_positives}/{actual})"
|
|
)
|
|
|
|
|
|
def test_overall_detection_goal_is_met() -> None:
|
|
totals = [_language_metrics(names) for names in LANGUAGE_MANIFESTS.values()]
|
|
expected = sum(t[0] for t in totals)
|
|
matched = sum(t[1] for t in totals)
|
|
actual = sum(t[2] for t in totals)
|
|
false_positives = sum(t[3] for t in totals)
|
|
|
|
assert matched / expected >= RECALL_FLOOR
|
|
assert (false_positives / actual) < FALSE_POSITIVE_CEILING
|