realvuln v3.1
Dashboard Methodology Dataset Findings Roadmap GitHub ↗
Scanner deep-dive

Kimi K3 by Moonshot AI ↗

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

59.4
F3 (strict)
60.7
F2 (strict)
58.2%
Recall (strict)
73.0%
Precision
66/66
Repos scored
kimi-k3
Model
$21
Total cost
380s
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)
pythonssti100 F2 · 100%
vfapi100 F2 · 100%
vampi87 F2 · 87%
dsvw82 F2 · 81%
python-app78 F2 · 76%
vulnpy78 F2 · 76%
insecure-web78 F2 · 78%
vc-kimi-code-seeded-v2-legal-case-django76 F2 · 77%
vc-codex-high-seeded-v2-hr-payroll-django75 F2 · 76%
vulnerable-api75 F2 · 71%
vc-kimi-code-seeded-v2-hr-payroll-django74 F2 · 72%
dsvpwa74 F2 · 72%
vc-codex-high-seeded-v2-education-lms-django74 F2 · 76%
vulnerable-tornado-app72 F2 · 71%
vc-kimi-code-seeded-v2-property-management-fastapi72 F2 · 70%
vc-kimi-code-seeded-v2-support-desk-fastapi72 F2 · 71%
owasp-web-playground71 F2 · 68%
dvblab70 F2 · 68%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi70 F2 · 68%
vc-claude-code-seeded-v2-legal-case-django70 F2 · 68%
vc-codex-high-seeded-v2-crm-saas-django69 F2 · 68%
vc-codex-seeded-v2-logistics-dispatch-fastapi66 F2 · 63%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi66 F2 · 67%
vc-kimi-code-seeded-v2-fintech-lending-fastapi66 F2 · 64%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi65 F2 · 65%
vc-codex-seeded-v2-marketplace-commerce-fastapi65 F2 · 62%
vc-codex-high-seeded-v2-fintech-lending-fastapi64 F2 · 69%
vc-kimi-code-seeded-v2-healthcare-clinic-django64 F2 · 67%
threatbyte64 F2 · 62%
pygoat64 F2 · 60%
vc-claude-code-seeded-v2-fintech-lending-fastapi64 F2 · 62%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi64 F2 · 62%
vc-claude-code-seeded-v2-support-desk-fastapi62 F2 · 59%
extremely-vulnerable-flask-app61 F2 · 56%
intentionally-vulnerable-python-application61 F2 · 57%
vc-codex-high-seeded-v2-support-desk-fastapi60 F2 · 57%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi60 F2 · 58%
vc-codex-seeded-v2-support-desk-fastapi60 F2 · 57%
vc-codex-high-seeded-v2-property-management-fastapi60 F2 · 62%
vulnerable-flask-app59 F2 · 57%
vc-claude-code-seeded-v2-crm-saas-django59 F2 · 57%
vc-claude-code-seeded-v2-education-lms-django59 F2 · 56%
vulnerable-python-apps58 F2 · 55%
vc-claude-code-seeded-v2-hr-payroll-django58 F2 · 56%
vc-codex-seeded-v2-hr-payroll-django58 F2 · 54%
vc-codex-seeded-v2-property-management-fastapi57 F2 · 55%
vc-claude-code-seeded-v2-healthcare-clinic-django57 F2 · 55%
vc-codex-seeded-v2-crm-saas-django57 F2 · 53%
vc-kimi-code-seeded-v2-education-lms-django56 F2 · 57%
python-insecure-app56 F2 · 50%
vc-claude-code-seeded-v2-property-management-fastapi56 F2 · 52%
vc-codex-seeded-v2-legal-case-django55 F2 · 52%
vc-codex-high-seeded-v2-healthcare-clinic-django55 F2 · 54%
vc-codex-seeded-v2-education-lms-django54 F2 · 51%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi53 F2 · 50%
vc-codex-seeded-v2-healthcare-clinic-django53 F2 · 51%
lets-be-bad-guys53 F2 · 50%
vc-kimi-code-seeded-v2-crm-saas-django53 F2 · 52%
djangoat52 F2 · 48%
damn-vulnerable-graphql-application48 F2 · 44%
damn-vulnerable-flask-application44 F2 · 43%
flask-xss42 F2 · 37%
vc-codex-seeded-v2-fintech-lending-fastapi42 F2 · 38%
dvpwa38 F2 · 35%
vc-codex-high-seeded-v2-legal-case-django24 F2 · 24%
vulpy0 F2 · 0%
RepositoryTPFPFNRecall %F2
pythonssti200100.0100.0
vfapi900100.0100.0
vampi132286.786.7
dsvw224581.582.1
python-app162576.278.4
vulnpy61101976.278.0
insecure-web72277.877.8
vc-kimi-code-seeded-v2-legal-case-django208676.975.8
vc-codex-high-seeded-v2-hr-payroll-django197676.075.4
vulnerable-api101471.474.6
vc-kimi-code-seeded-v2-hr-payroll-django215872.473.9
dsvpwa235971.973.7
vc-codex-high-seeded-v2-education-lms-django1910676.073.6
vulnerable-tornado-app103471.472.5
vc-kimi-code-seeded-v2-property-management-fastapi215970.071.9
vc-kimi-code-seeded-v2-support-desk-fastapi207871.471.9
owasp-web-playground193967.970.9
dvblab154768.270.1
vc-codex-high-seeded-v2-marketplace-commerce-fastapi175868.069.7
vc-claude-code-seeded-v2-legal-case-django2161067.769.5
vc-codex-high-seeded-v2-crm-saas-django176868.069.1
vc-codex-seeded-v2-logistics-dispatch-fastapi1941163.366.4
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi1810966.766.2
vc-kimi-code-seeded-v2-fintech-lending-fastapi2171263.665.6
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi2091164.565.4
vc-codex-seeded-v2-marketplace-commerce-fastapi1851162.164.7
vc-codex-high-seeded-v2-fintech-lending-fastapi2019969.064.5
vc-kimi-code-seeded-v2-healthcare-clinic-django20151066.764.5
threatbyte1651061.564.0
pygoat4793160.363.9
vc-claude-code-seeded-v2-fintech-lending-fastapi1871162.163.8
vc-codex-high-seeded-v2-logistics-dispatch-fastapi1871162.163.8
vc-claude-code-seeded-v2-support-desk-fastapi2041458.862.5
extremely-vulnerable-flask-app1821456.260.8
intentionally-vulnerable-python-application41357.160.6
vc-codex-high-seeded-v2-support-desk-fastapi1651257.160.2
vc-claude-code-seeded-v2-logistics-dispatch-fastapi1971457.660.1
vc-codex-seeded-v2-support-desk-fastapi1751356.759.9
vc-codex-high-seeded-v2-property-management-fastapi16141061.559.7
vulnerable-flask-app125957.159.4
vc-claude-code-seeded-v2-crm-saas-django1671257.159.3
vc-claude-code-seeded-v2-education-lms-django1861456.259.2
vulnerable-python-apps1231054.558.3
vc-claude-code-seeded-v2-hr-payroll-django1561255.658.1
vc-codex-seeded-v2-hr-payroll-django2141853.858.0
vc-codex-seeded-v2-property-management-fastapi1771454.857.4
vc-claude-code-seeded-v2-healthcare-clinic-django1681355.257.1
vc-codex-seeded-v2-crm-saas-django1851652.956.6
vc-kimi-code-seeded-v2-education-lms-django16141257.156.3
python-insecure-app40450.055.6
vc-claude-code-seeded-v2-property-management-fastapi1741651.555.6
vc-codex-seeded-v2-legal-case-django1751651.555.2
vc-codex-high-seeded-v2-healthcare-clinic-django14101253.854.7
vc-codex-seeded-v2-education-lms-django1891751.453.9
vc-claude-code-seeded-v2-marketplace-commerce-fastapi1661650.053.3
vc-codex-seeded-v2-healthcare-clinic-django21122051.253.3
lets-be-bad-guys1251250.053.1
vc-kimi-code-seeded-v2-crm-saas-django14111351.852.6
djangoat2592748.151.7
damn-vulnerable-graphql-application1662044.448.2
damn-vulnerable-flask-application66842.944.1
flask-xss1111936.741.7
vc-codex-seeded-v2-fintech-lending-fastapi1462337.841.7
dvpwa851534.838.1
vc-codex-high-seeded-v2-legal-case-django6191924.024.0
vulpy00570.00.0
§

Detection by severity

SeverityTPFPFNRecall %
Critical14201292.2
High468228462.2
Medium451145949.6
Low4604053.5
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
Open Redirect4000100.0
HTTP Header Injection200100.0
XPath Injection400100.0
Command / OS Injection470295.9
Insecure Deserialization370392.5
XML External Entities350392.1
Code Injection / RFI310391.2
SQL Injection710791.0
Path Traversal381686.4
Security Misconfiguration8003271.4
Hardcoded Credentials4802070.6
Server-Side Request Forgery2821368.3
Denial of Service2701761.4
Cross-Site Scripting6704360.9
Sensitive Data Exposure8107452.3
Missing Authentication / Authorization4204150.6
Other406047146.3
Broken Access Control / IDOR2306027.7
§

LLM operational metrics

53,273
Avg input tokens
10,894
Avg output tokens
385,393
Avg total tokens
380s
Avg latency / repo
1.5%
JSON repair rate
66
Total runs
§

Cost

$21
Total cost
$0.32
Cost / run
$0.016
Cost / 100 LOC
133,782
Lines of code scanned
66
Successful runs

← Back to the leaderboard