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

Kimi K2.5 by Moonshot AI ↗

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

46.1
F3 (strict)
48.1
F2 (strict)
44.3%
Recall (strict)
72.4%
Precision
66/66
Repos scored
kimi-k2.5
Model
$8
Total cost
127s
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)
vfapi84 F2 · 89%
vulnpy74 F2 · 71%
intentionally-vulnerable-python-application70 F2 · 67%
dsvw69 F2 · 65%
insecure-web68 F2 · 67%
lets-be-bad-guys67 F2 · 65%
python-app63 F2 · 62%
vampi62 F2 · 62%
dsvpwa58 F2 · 54%
dvblab57 F2 · 55%
vulnerable-api56 F2 · 52%
vc-codex-high-seeded-v2-education-lms-django55 F2 · 52%
damn-vulnerable-flask-application55 F2 · 56%
vc-codex-high-seeded-v2-property-management-fastapi55 F2 · 51%
vc-claude-code-seeded-v2-fintech-lending-fastapi54 F2 · 51%
vc-codex-seeded-v2-logistics-dispatch-fastapi53 F2 · 49%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi53 F2 · 48%
vulnerable-flask-app53 F2 · 51%
vc-codex-high-seeded-v2-crm-saas-django53 F2 · 49%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi52 F2 · 49%
pythonssti52 F2 · 50%
vc-claude-code-seeded-v2-crm-saas-django52 F2 · 48%
vc-codex-high-seeded-v2-fintech-lending-fastapi52 F2 · 47%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi51 F2 · 47%
vc-kimi-code-seeded-v2-property-management-fastapi51 F2 · 47%
vc-kimi-code-seeded-v2-crm-saas-django51 F2 · 48%
vulnerable-python-apps51 F2 · 48%
dvpwa50 F2 · 49%
vc-kimi-code-seeded-v2-legal-case-django50 F2 · 46%
vc-codex-high-seeded-v2-support-desk-fastapi50 F2 · 45%
python-insecure-app49 F2 · 46%
vulnerable-tornado-app49 F2 · 45%
threatbyte49 F2 · 49%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi49 F2 · 45%
vc-kimi-code-seeded-v2-hr-payroll-django49 F2 · 45%
vc-kimi-code-seeded-v2-fintech-lending-fastapi49 F2 · 45%
vc-kimi-code-seeded-v2-support-desk-fastapi48 F2 · 45%
vc-claude-code-seeded-v2-hr-payroll-django48 F2 · 43%
vc-codex-seeded-v2-marketplace-commerce-fastapi47 F2 · 43%
vc-codex-seeded-v2-crm-saas-django46 F2 · 42%
owasp-web-playground46 F2 · 43%
pygoat45 F2 · 44%
vc-codex-high-seeded-v2-hr-payroll-django45 F2 · 41%
vc-claude-code-seeded-v2-support-desk-fastapi44 F2 · 39%
vc-codex-high-seeded-v2-legal-case-django44 F2 · 40%
vc-kimi-code-seeded-v2-education-lms-django44 F2 · 40%
extremely-vulnerable-flask-app44 F2 · 40%
vc-claude-code-seeded-v2-education-lms-django44 F2 · 40%
vc-codex-seeded-v2-legal-case-django44 F2 · 39%
vc-codex-seeded-v2-support-desk-fastapi44 F2 · 39%
vc-codex-seeded-v2-hr-payroll-django43 F2 · 38%
vc-codex-high-seeded-v2-healthcare-clinic-django42 F2 · 38%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi42 F2 · 38%
vc-claude-code-seeded-v2-healthcare-clinic-django41 F2 · 38%
vc-codex-seeded-v2-property-management-fastapi40 F2 · 35%
vc-codex-seeded-v2-fintech-lending-fastapi40 F2 · 36%
vc-kimi-code-seeded-v2-healthcare-clinic-django39 F2 · 36%
damn-vulnerable-graphql-application39 F2 · 35%
vc-claude-code-seeded-v2-legal-case-django38 F2 · 34%
flask-xss37 F2 · 34%
vc-codex-seeded-v2-education-lms-django36 F2 · 31%
vc-claude-code-seeded-v2-property-management-fastapi35 F2 · 30%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi33 F2 · 30%
vc-codex-seeded-v2-healthcare-clinic-django33 F2 · 29%
djangoat31 F2 · 28%
vulpy30 F2 · 26%
RepositoryTPFPFNRecall %F2
vfapi84188.983.9
vulnpy5732371.274.5
intentionally-vulnerable-python-application51266.770.1
dsvw182965.468.9
insecure-web62366.768.5
lets-be-bad-guys164865.367.4
python-app136861.963.3
vampi96662.261.8
dsvpwa1751554.257.7
dvblab1261054.556.8
vulnerable-api72752.456.1
vc-codex-high-seeded-v2-education-lms-django1351252.055.1
damn-vulnerable-flask-application87755.554.8
vc-codex-high-seeded-v2-property-management-fastapi1351351.354.7
vc-claude-code-seeded-v2-fintech-lending-fastapi1561450.653.5
vc-codex-seeded-v2-logistics-dispatch-fastapi1531548.953.0
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi1321448.153.0
vulnerable-flask-app1161050.852.9
vc-codex-high-seeded-v2-crm-saas-django1241349.352.8
vc-codex-high-seeded-v2-marketplace-commerce-fastapi1261349.352.3
pythonssti11150.051.9
vc-claude-code-seeded-v2-crm-saas-django1441448.251.9
vc-codex-high-seeded-v2-fintech-lending-fastapi1421547.151.8
vc-codex-high-seeded-v2-logistics-dispatch-fastapi1431547.151.3
vc-kimi-code-seeded-v2-property-management-fastapi1421646.751.3
vc-kimi-code-seeded-v2-crm-saas-django1361448.151.2
vulnerable-python-apps1161148.551.0
dvpwa1191249.350.3
vc-kimi-code-seeded-v2-legal-case-django1231446.250.2
vc-codex-high-seeded-v2-support-desk-fastapi1331545.249.6
python-insecure-app41445.849.4
vulnerable-tornado-app62845.249.4
threatbyte13131348.749.0
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi1451745.249.0
vc-kimi-code-seeded-v2-hr-payroll-django1341644.848.9
vc-kimi-code-seeded-v2-fintech-lending-fastapi1571845.548.6
vc-kimi-code-seeded-v2-support-desk-fastapi1371545.248.2
vc-claude-code-seeded-v2-hr-payroll-django1221543.247.7
vc-codex-seeded-v2-marketplace-commerce-fastapi1241742.546.6
vc-codex-seeded-v2-crm-saas-django1462042.245.8
owasp-web-playground1271642.945.6
pygoat34324444.045.1
vc-codex-high-seeded-v2-hr-payroll-django1051541.345.0
vc-claude-code-seeded-v2-support-desk-fastapi1312139.244.2
vc-codex-high-seeded-v2-legal-case-django1031540.044.2
vc-kimi-code-seeded-v2-education-lms-django1151740.544.2
extremely-vulnerable-flask-app1331939.644.0
vc-claude-code-seeded-v2-education-lms-django1341939.643.8
vc-codex-seeded-v2-legal-case-django1342039.443.7
vc-codex-seeded-v2-support-desk-fastapi1221838.943.6
vc-codex-seeded-v2-hr-payroll-django1532438.543.1
vc-codex-high-seeded-v2-healthcare-clinic-django1041638.542.1
vc-claude-code-seeded-v2-logistics-dispatch-fastapi1362038.441.9
vc-claude-code-seeded-v2-healthcare-clinic-django1181837.940.9
vc-codex-seeded-v2-property-management-fastapi1122035.539.8
vc-codex-seeded-v2-fintech-lending-fastapi1372436.039.7
vc-kimi-code-seeded-v2-healthcare-clinic-django1151935.539.3
damn-vulnerable-graphql-application1382335.238.6
vc-claude-code-seeded-v2-legal-case-django1042033.938.0
flask-xss1072034.437.1
vc-codex-seeded-v2-education-lms-django1132431.435.8
vc-claude-code-seeded-v2-property-management-fastapi1012330.334.8
vc-claude-code-seeded-v2-marketplace-commerce-fastapi1052229.733.3
vc-codex-seeded-v2-healthcare-clinic-django1242929.333.3
djangoat1473827.631.2
vulpy1564225.729.5
§

Detection by severity

SeverityTPFPFNRecall %
Critical13701888.4
High336741644.7
Medium325258535.7
Low3105536.0
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
Code Injection / RFI3400100.0
XPath Injection400100.0
XML External Entities371197.4
Insecure Deserialization380295.0
Open Redirect380295.0
SQL Injection734593.6
Command / OS Injection441688.0
Path Traversal3411077.3
Server-Side Request Forgery2901270.7
Cross-Site Scripting6504559.1
Hardcoded Credentials3803055.9
HTTP Header Injection10150.0
Security Misconfiguration4706542.0
Sensitive Data Exposure53010234.2
Other263061430.0
Missing Authentication / Authorization1626719.3
Broken Access Control / IDOR1207114.5
Denial of Service30416.8
§

LLM operational metrics

35,305
Avg input tokens
5,278
Avg output tokens
203,853
Avg total tokens
127s
Avg latency / repo
0.5%
JSON repair rate
198
Total runs
±10.3
F2 run-to-run σ
§

Cost

$8
Total cost
$0.04
Cost / run
$0.002
Cost / 100 LOC
133,782
Python LOC scanned
192
Successful runs

← Back to the leaderboard