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

Gemma 4 31B by Google ↗

General-Purpose LLM · agentic-v1 · scored on 66/66 repositories. Strict scoring (unfinished repos counted as misses).

Methodology note
Locally hosted. Open-weight GGUF (Q4_K_M) via Ollama, standard agentic-v1 harness. Cost $0 (self-hosted).
25.4
F3 (strict)
27.6
F2 (strict)
23.5%
Recall (strict)
90.3%
Precision
66/66
Repos scored
gemma4-31b
Model
Free
Total cost
304s
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-application61 F2 · 57%
insecure-web60 F2 · 56%
vampi58 F2 · 53%
pythonssti56 F2 · 50%
dsvw54 F2 · 48%
vc-codex-high-seeded-v2-hr-payroll-django54 F2 · 48%
damn-vulnerable-flask-application52 F2 · 47%
dvblab51 F2 · 45%
dsvpwa49 F2 · 44%
vulnerable-api48 F2 · 43%
vc-kimi-code-seeded-v2-fintech-lending-fastapi48 F2 · 42%
lets-be-bad-guys47 F2 · 42%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi46 F2 · 41%
vc-codex-seeded-v2-logistics-dispatch-fastapi46 F2 · 40%
python-app44 F2 · 38%
vc-codex-high-seeded-v2-property-management-fastapi43 F2 · 38%
python-insecure-app43 F2 · 38%
vc-codex-seeded-v2-fintech-lending-fastapi43 F2 · 38%
vc-claude-code-seeded-v2-fintech-lending-fastapi43 F2 · 38%
vulnerable-tornado-app41 F2 · 36%
vc-kimi-code-seeded-v2-education-lms-django40 F2 · 36%
vc-claude-code-seeded-v2-legal-case-django40 F2 · 35%
owasp-web-playground40 F2 · 36%
vc-claude-code-seeded-v2-crm-saas-django37 F2 · 32%
vc-codex-high-seeded-v2-legal-case-django37 F2 · 32%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi37 F2 · 32%
vulnerable-python-apps36 F2 · 32%
vc-codex-high-seeded-v2-fintech-lending-fastapi36 F2 · 31%
vc-claude-code-seeded-v2-support-desk-fastapi34 F2 · 29%
vulnpy34 F2 · 29%
vc-kimi-code-seeded-v2-support-desk-fastapi33 F2 · 29%
vc-codex-seeded-v2-hr-payroll-django33 F2 · 28%
vc-codex-high-seeded-v2-education-lms-django32 F2 · 28%
vc-codex-seeded-v2-marketplace-commerce-fastapi32 F2 · 28%
vc-codex-high-seeded-v2-healthcare-clinic-django32 F2 · 27%
threatbyte31 F2 · 27%
vc-codex-seeded-v2-crm-saas-django31 F2 · 26%
vc-kimi-code-seeded-v2-crm-saas-django30 F2 · 26%
damn-vulnerable-graphql-application29 F2 · 25%
vc-claude-code-seeded-v2-education-lms-django29 F2 · 25%
vc-codex-seeded-v2-legal-case-django28 F2 · 24%
vc-kimi-code-seeded-v2-hr-payroll-django28 F2 · 24%
vc-codex-seeded-v2-support-desk-fastapi27 F2 · 23%
pygoat27 F2 · 23%
vc-codex-seeded-v2-education-lms-django27 F2 · 23%
vc-codex-seeded-v2-healthcare-clinic-django26 F2 · 22%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi26 F2 · 22%
dvpwa26 F2 · 22%
flask-xss23 F2 · 20%
vulpy15 F2 · 12%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi4 F2 · 3%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi4 F2 · 3%
djangoat0 F2 · 0%
extremely-vulnerable-flask-app0 F2 · 0%
vfapi0 F2 · 0%
vulnerable-flask-app0 F2 · 0%
vc-claude-code-seeded-v2-healthcare-clinic-django0 F2 · 0%
vc-claude-code-seeded-v2-hr-payroll-django0 F2 · 0%
vc-claude-code-seeded-v2-property-management-fastapi0 F2 · 0%
vc-codex-high-seeded-v2-crm-saas-django0 F2 · 0%
vc-codex-high-seeded-v2-support-desk-fastapi0 F2 · 0%
vc-codex-seeded-v2-property-management-fastapi0 F2 · 0%
vc-kimi-code-seeded-v2-healthcare-clinic-django0 F2 · 0%
vc-kimi-code-seeded-v2-legal-case-django0 F2 · 0%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi0 F2 · 0%
vc-kimi-code-seeded-v2-property-management-fastapi0 F2 · 0%
RepositoryTPFPFNRecall %F2
intentionally-vulnerable-python-application41357.160.6
insecure-web51455.659.5
vampi81753.358.0
pythonssti10150.055.6
dsvw1301448.153.7
vc-codex-high-seeded-v2-hr-payroll-django1201348.053.6
damn-vulnerable-flask-application70846.752.2
dvblab1001245.551.0
dsvpwa1411843.849.0
vulnerable-api60842.948.4
vc-kimi-code-seeded-v2-fintech-lending-fastapi1401942.447.9
lets-be-bad-guys1001441.747.2
vc-codex-high-seeded-v2-logistics-dispatch-fastapi1211741.446.5
vc-codex-seeded-v2-logistics-dispatch-fastapi1201840.045.5
python-app801338.143.5
vc-codex-high-seeded-v2-property-management-fastapi1021638.543.1
python-insecure-app30537.542.9
vc-codex-seeded-v2-fintech-lending-fastapi1422337.842.7
vc-claude-code-seeded-v2-fintech-lending-fastapi1121837.942.6
vulnerable-tornado-app50935.741.0
vc-kimi-code-seeded-v2-education-lms-django1021835.740.3
vc-claude-code-seeded-v2-legal-case-django1122035.540.1
owasp-web-playground1031835.740.0
vc-claude-code-seeded-v2-crm-saas-django901932.137.2
vc-codex-high-seeded-v2-legal-case-django801732.037.0
vc-codex-high-seeded-v2-marketplace-commerce-fastapi801732.037.0
vulnerable-python-apps721531.836.1
vc-codex-high-seeded-v2-fintech-lending-fastapi902031.036.0
vc-claude-code-seeded-v2-support-desk-fastapi1012429.434.0
vulnpy2305728.733.5
vc-kimi-code-seeded-v2-support-desk-fastapi802028.633.3
vc-codex-seeded-v2-hr-payroll-django1112828.232.7
vc-codex-high-seeded-v2-education-lms-django711828.032.4
vc-codex-seeded-v2-marketplace-commerce-fastapi812127.632.0
vc-codex-high-seeded-v2-healthcare-clinic-django701926.931.5
threatbyte721926.931.0
vc-codex-seeded-v2-crm-saas-django902526.531.0
vc-kimi-code-seeded-v2-crm-saas-django712025.930.2
damn-vulnerable-graphql-application902725.029.4
vc-claude-code-seeded-v2-education-lms-django812425.029.2
vc-codex-seeded-v2-legal-case-django812524.228.4
vc-kimi-code-seeded-v2-hr-payroll-django722224.128.0
vc-codex-seeded-v2-support-desk-fastapi722323.327.1
pygoat1866023.126.8
vc-codex-seeded-v2-education-lms-django812722.926.8
vc-codex-seeded-v2-healthcare-clinic-django903221.926.0
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi622122.225.9
dvpwa501821.725.8
flask-xss622420.023.4
vulpy725012.314.8
vc-claude-code-seeded-v2-marketplace-commerce-fastapi11313.13.8
vc-claude-code-seeded-v2-logistics-dispatch-fastapi11323.03.7
djangoat00520.00.0
extremely-vulnerable-flask-app00320.00.0
vfapi0090.00.0
vulnerable-flask-app00210.00.0
vc-claude-code-seeded-v2-healthcare-clinic-django00290.00.0
vc-claude-code-seeded-v2-hr-payroll-django00270.00.0
vc-claude-code-seeded-v2-property-management-fastapi00330.00.0
vc-codex-high-seeded-v2-crm-saas-django00250.00.0
vc-codex-high-seeded-v2-support-desk-fastapi00280.00.0
vc-codex-seeded-v2-property-management-fastapi00310.00.0
vc-kimi-code-seeded-v2-healthcare-clinic-django00300.00.0
vc-kimi-code-seeded-v2-legal-case-django00260.00.0
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi00310.00.0
vc-kimi-code-seeded-v2-property-management-fastapi00300.00.0
§

Detection by severity

SeverityTPFPFNRecall %
Critical9905663.9
High219153329.1
Medium124178613.6
Low60807.0
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
XML External Entities2811073.7
Command / OS Injection3401668.0
Code Injection / RFI2301167.6
Open Redirect2701367.5
SQL Injection5102765.4
Insecure Deserialization2601465.0
Path Traversal2501956.8
HTTP Header Injection10150.0
Server-Side Request Forgery1802343.9
Cross-Site Scripting3907135.5
XPath Injection10325.0
Security Misconfiguration2109118.8
Hardcoded Credentials1215617.6
Other117076013.3
Broken Access Control / IDOR907410.8
Missing Authentication / Authorization50786.0
Sensitive Data Exposure901465.8
Denial of Service20424.5
§

LLM operational metrics

122,874
Avg input tokens
4,404
Avg output tokens
127,278
Avg total tokens
304s
Avg latency / repo
19.7%
JSON repair rate
66
Total runs
§

Cost

Free
Total cost
133,782
Python LOC scanned
66
Successful runs

← Back to the leaderboard