realvuln v2.0
Dashboard Methodology Dataset Findings Roadmap GitHub ↗
Scanner deep-dive

Anthropic Method - Sonnet 4.6 by Kolega Scan OSS ↗

Security-Specialized · Claude Code · scored on 66/66 repositories. Strict scoring (unfinished repos counted as misses).

47.9
F3 (strict)
49.5
F2 (strict)
46.5%
Recall (strict)
67.0%
Precision
66/66
Repos scored
claude-sonnet-4-6
Model
$291
Total cost
397s
Avg latency
§

Per-repository breakdown

Each bar shows true positives, false positives, and misses on one repository; bar length is proportional to that repo's labeled vulnerabilities. Ranked by F2.

True positiveFalse positiveMissed (FN)
intentionally-vulnerable-python-application88 F2 · 86%
damn-vulnerable-flask-application74 F2 · 73%
dsvw71 F2 · 67%
insecure-web71 F2 · 67%
vc-kimi-code-seeded-v2-legal-case-django71 F2 · 81%
vc-codex-high-seeded-v2-crm-saas-django70 F2 · 76%
vfapi70 F2 · 67%
vampi68 F2 · 73%
vc-codex-high-seeded-v2-education-lms-django66 F2 · 64%
vc-codex-high-seeded-v2-legal-case-django66 F2 · 64%
vc-kimi-code-seeded-v2-property-management-fastapi63 F2 · 63%
vc-codex-seeded-v2-legal-case-django62 F2 · 58%
vc-codex-high-seeded-v2-hr-payroll-django62 F2 · 60%
vc-kimi-code-seeded-v2-healthcare-clinic-django62 F2 · 63%
vulnerable-tornado-app62 F2 · 57%
vc-codex-seeded-v2-hr-payroll-django62 F2 · 59%
vc-codex-seeded-v2-logistics-dispatch-fastapi61 F2 · 57%
vc-claude-code-seeded-v2-legal-case-django61 F2 · 58%
vc-codex-seeded-v2-crm-saas-django61 F2 · 59%
vc-codex-seeded-v2-healthcare-clinic-django61 F2 · 59%
vc-codex-high-seeded-v2-healthcare-clinic-django60 F2 · 62%
vc-kimi-code-seeded-v2-support-desk-fastapi59 F2 · 54%
vc-codex-high-seeded-v2-support-desk-fastapi58 F2 · 57%
owasp-web-playground58 F2 · 54%
vc-claude-code-seeded-v2-education-lms-django58 F2 · 56%
vc-claude-code-seeded-v2-fintech-lending-fastapi58 F2 · 55%
vc-codex-high-seeded-v2-fintech-lending-fastapi57 F2 · 55%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi56 F2 · 52%
vc-claude-code-seeded-v2-property-management-fastapi56 F2 · 52%
python-app56 F2 · 52%
vc-claude-code-seeded-v2-hr-payroll-django56 F2 · 52%
python-insecure-app56 F2 · 50%
pythonssti56 F2 · 50%
dvblab55 F2 · 55%
extremely-vulnerable-flask-app54 F2 · 50%
vc-claude-code-seeded-v2-crm-saas-django53 F2 · 54%
vc-kimi-code-seeded-v2-fintech-lending-fastapi53 F2 · 52%
vc-codex-seeded-v2-marketplace-commerce-fastapi53 F2 · 48%
vc-claude-code-seeded-v2-healthcare-clinic-django52 F2 · 52%
vc-claude-code-seeded-v2-support-desk-fastapi52 F2 · 47%
vulnerable-flask-app52 F2 · 48%
vc-codex-seeded-v2-education-lms-django51 F2 · 46%
threatbyte50 F2 · 46%
lets-be-bad-guys50 F2 · 46%
vc-codex-seeded-v2-property-management-fastapi49 F2 · 45%
dsvpwa49 F2 · 44%
vulnerable-api48 F2 · 43%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi48 F2 · 48%
vc-kimi-code-seeded-v2-crm-saas-django48 F2 · 48%
vc-codex-high-seeded-v2-property-management-fastapi46 F2 · 42%
flask-xss45 F2 · 40%
vulnpy45 F2 · 41%
vc-codex-seeded-v2-support-desk-fastapi45 F2 · 40%
vc-kimi-code-seeded-v2-hr-payroll-django41 F2 · 41%
vulnerable-python-apps38 F2 · 36%
pygoat38 F2 · 35%
djangoat37 F2 · 35%
damn-vulnerable-graphql-application36 F2 · 33%
dvpwa34 F2 · 30%
vulpy30 F2 · 26%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi24 F2 · 23%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi21 F2 · 19%
vc-kimi-code-seeded-v2-education-lms-django16 F2 · 14%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi7 F2 · 6%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi0 F2 · 0%
vc-codex-seeded-v2-fintech-lending-fastapi0 F2 · 0%
RepositoryTPFPFNRecall %F2
intentionally-vulnerable-python-application60185.788.2
damn-vulnerable-flask-application113473.374.3
dsvw180966.771.4
insecure-web60366.771.4
vc-kimi-code-seeded-v2-legal-case-django2122580.871.4
vc-codex-high-seeded-v2-crm-saas-django1916676.070.4
vfapi61366.769.8
vampi1110473.367.9
vc-codex-high-seeded-v2-education-lms-django165964.066.1
vc-codex-high-seeded-v2-legal-case-django166964.065.6
vc-kimi-code-seeded-v2-property-management-fastapi19111163.363.3
vc-codex-seeded-v2-legal-case-django1921457.662.1
vc-codex-high-seeded-v2-hr-payroll-django1561060.062.0
vc-kimi-code-seeded-v2-healthcare-clinic-django19151163.361.7
vulnerable-tornado-app81657.161.5
vc-codex-seeded-v2-hr-payroll-django2381659.061.5
vc-codex-seeded-v2-logistics-dispatch-fastapi1721356.761.2
vc-claude-code-seeded-v2-legal-case-django1861358.160.8
vc-codex-seeded-v2-crm-saas-django2091458.860.6
vc-codex-seeded-v2-healthcare-clinic-django24101758.560.6
vc-codex-high-seeded-v2-healthcare-clinic-django16141061.559.7
vc-kimi-code-seeded-v2-support-desk-fastapi1511353.658.6
vc-codex-high-seeded-v2-support-desk-fastapi1691257.158.4
owasp-web-playground1521353.658.1
vc-claude-code-seeded-v2-education-lms-django1891456.258.1
vc-claude-code-seeded-v2-fintech-lending-fastapi1671355.257.6
vc-codex-high-seeded-v2-fintech-lending-fastapi1681355.257.1
vc-codex-high-seeded-v2-marketplace-commerce-fastapi1321252.056.5
vc-claude-code-seeded-v2-property-management-fastapi1721651.556.3
python-app1131052.456.1
vc-claude-code-seeded-v2-hr-payroll-django1431351.856.0
python-insecure-app40450.055.6
pythonssti10150.055.6
dvblab1291054.555.0
extremely-vulnerable-flask-app1651650.053.7
vc-claude-code-seeded-v2-crm-saas-django15141353.653.2
vc-kimi-code-seeded-v2-fintech-lending-fastapi17111651.553.1
vc-codex-seeded-v2-marketplace-commerce-fastapi1421548.353.0
vc-claude-code-seeded-v2-healthcare-clinic-django15131451.752.1
vc-claude-code-seeded-v2-support-desk-fastapi1621847.151.9
vulnerable-flask-app1031147.651.5
vc-codex-seeded-v2-education-lms-django1621945.750.6
threatbyte1241446.250.0
lets-be-bad-guys1141345.849.5
vc-codex-seeded-v2-property-management-fastapi1441745.249.3
dsvpwa1411843.849.0
vulnerable-api60842.948.4
vc-codex-high-seeded-v2-logistics-dispatch-fastapi14161548.347.9
vc-kimi-code-seeded-v2-crm-saas-django13151448.147.8
vc-codex-high-seeded-v2-property-management-fastapi1141542.346.2
flask-xss1211840.045.1
vulnpy33134741.245.1
vc-codex-seeded-v2-support-desk-fastapi1221840.044.8
vc-kimi-code-seeded-v2-hr-payroll-django12181741.441.1
vulnerable-python-apps891436.438.1
pygoat27175134.637.9
djangoat18193434.636.7
damn-vulnerable-graphql-application12102433.336.1
dvpwa751630.433.7
vulpy1564226.330.1
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi7152422.624.0
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi582218.520.7
vc-kimi-code-seeded-v2-education-lms-django482414.316.1
vc-claude-code-seeded-v2-logistics-dispatch-fastapi22316.17.4
vc-claude-code-seeded-v2-marketplace-commerce-fastapi01320.00.0
vc-codex-seeded-v2-fintech-lending-fastapi00370.00.0
§

Detection by severity

SeverityTPFPFNRecall %
Critical12902683.2
High398335452.9
Medium3341457636.7
Low2306326.7
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
HTTP Header Injection200100.0
Insecure Deserialization330782.5
Command / OS Injection410982.0
XML External Entities311781.6
SQL Injection6211679.5
Code Injection / RFI270779.4
Open Redirect310977.5
Path Traversal2911565.9
Server-Side Request Forgery2421758.5
Security Misconfiguration5805451.8
XPath Injection20250.0
Missing Authentication / Authorization35114842.2
Hardcoded Credentials2714139.7
Other348052939.7
Broken Access Control / IDOR3205138.6
Sensitive Data Exposure5809737.4
Cross-Site Scripting4106937.3
Denial of Service30416.8
§

LLM operational metrics

169
Avg input tokens
25,487
Avg output tokens
3,597,481
Avg total tokens
397s
Avg latency / repo
0.0%
JSON repair rate
66
Total runs
§

Cost

$291
Total cost
$4.40
Cost / run
$0.217
Cost / 100 LOC
133,782
Python LOC scanned
66
Successful runs

← Back to the leaderboard