Scanner deep-dive
Anthropic Method (DeepSeek V4 Pro) by Kolega Scan OSS ↗
Security-Specialized · Bespoke Adaptation · scored on 66/66 repositories. Strict scoring (unfinished repos counted as misses).
51.3
F3 (strict)
50.8
F2 (strict)
51.8%
Recall (strict)
46.9%
Precision
66/66
Repos scored
—
Model
Free
Total cost
—
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.
| Repository | TP | FP | FN | Recall % | F2 |
|---|---|---|---|---|---|
| pythonssti | 2 | 1 | 0 | 100.0 | 90.9 |
| dsvw | 23 | 2 | 4 | 85.2 | 86.5 |
| intentionally-vulnerable-python-application | 6 | 2 | 1 | 85.7 | 83.3 |
| dsvpwa | 22 | 3 | 10 | 68.8 | 71.9 |
| vampi | 12 | 15 | 3 | 80.0 | 69.0 |
| lets-be-bad-guys | 16 | 5 | 8 | 66.7 | 68.4 |
| vc-kimi-code-seeded-v2-property-management-fastapi | 21 | 16 | 9 | 70.0 | 66.9 |
| insecure-web | 6 | 3 | 3 | 66.7 | 66.7 |
| vc-kimi-code-seeded-v2-crm-saas-django | 20 | 23 | 7 | 74.1 | 66.2 |
| damn-vulnerable-graphql-application | 25 | 28 | 11 | 69.4 | 63.5 |
| vulnerable-tornado-app | 9 | 6 | 5 | 64.3 | 63.4 |
| owasp-web-playground | 17 | 6 | 11 | 60.7 | 63.0 |
| vc-codex-high-seeded-v2-marketplace-commerce-fastapi | 17 | 19 | 8 | 68.0 | 62.5 |
| threatbyte | 16 | 9 | 10 | 61.5 | 62.0 |
| vc-codex-high-seeded-v2-fintech-lending-fastapi | 21 | 33 | 8 | 72.4 | 61.8 |
| vc-codex-seeded-v2-property-management-fastapi | 19 | 11 | 12 | 61.3 | 61.7 |
| vfapi | 6 | 7 | 3 | 66.7 | 61.2 |
| vc-kimi-code-seeded-v2-support-desk-fastapi | 18 | 19 | 10 | 64.3 | 60.4 |
| vc-kimi-code-seeded-v2-marketplace-commerce-fastapi | 16 | 9 | 11 | 59.3 | 60.2 |
| vc-codex-seeded-v2-hr-payroll-django | 24 | 20 | 15 | 61.5 | 60.0 |
| vc-claude-code-seeded-v2-support-desk-fastapi | 21 | 19 | 13 | 61.8 | 59.7 |
| extremely-vulnerable-flask-app | 19 | 13 | 13 | 59.4 | 59.4 |
| vulnerable-flask-app | 12 | 5 | 9 | 57.1 | 59.4 |
| vc-codex-seeded-v2-legal-case-django | 20 | 17 | 13 | 60.6 | 59.2 |
| vc-claude-code-seeded-v2-legal-case-django | 21 | 34 | 10 | 67.7 | 58.7 |
| vc-codex-seeded-v2-marketplace-commerce-fastapi | 17 | 12 | 12 | 58.6 | 58.6 |
| vc-claude-code-seeded-v2-crm-saas-django | 18 | 25 | 10 | 64.3 | 58.1 |
| vc-codex-high-seeded-v2-support-desk-fastapi | 17 | 18 | 11 | 60.7 | 57.8 |
| dvblab | 14 | 20 | 8 | 63.6 | 57.4 |
| vc-claude-code-seeded-v2-hr-payroll-django | 17 | 23 | 10 | 63.0 | 57.4 |
| vc-codex-seeded-v2-logistics-dispatch-fastapi | 19 | 28 | 11 | 63.3 | 56.9 |
| vc-codex-high-seeded-v2-logistics-dispatch-fastapi | 17 | 17 | 12 | 58.6 | 56.7 |
| vc-codex-high-seeded-v2-healthcare-clinic-django | 16 | 22 | 10 | 61.5 | 56.3 |
| vc-codex-seeded-v2-support-desk-fastapi | 16 | 7 | 14 | 53.3 | 55.9 |
| vulnerable-api | 7 | 2 | 7 | 50.0 | 53.8 |
| vc-codex-seeded-v2-crm-saas-django | 22 | 48 | 12 | 64.7 | 53.4 |
| vulpy | 29 | 17 | 28 | 50.9 | 52.9 |
| vc-codex-seeded-v2-education-lms-django | 18 | 13 | 17 | 51.4 | 52.6 |
| vc-codex-high-seeded-v2-education-lms-django | 13 | 13 | 12 | 52.0 | 51.6 |
| vc-kimi-code-seeded-v2-fintech-lending-fastapi | 17 | 19 | 16 | 51.5 | 50.6 |
| vc-kimi-code-seeded-v2-legal-case-django | 18 | 56 | 8 | 69.2 | 50.6 |
| vc-kimi-code-seeded-v2-hr-payroll-django | 20 | 65 | 9 | 69.0 | 49.8 |
| vc-codex-seeded-v2-healthcare-clinic-django | 21 | 31 | 20 | 51.2 | 48.6 |
| vc-codex-seeded-v2-fintech-lending-fastapi | 16 | 3 | 21 | 43.2 | 47.9 |
| vc-codex-high-seeded-v2-legal-case-django | 12 | 16 | 13 | 48.0 | 46.9 |
| vc-claude-code-seeded-v2-education-lms-django | 16 | 27 | 16 | 50.0 | 46.8 |
| vc-codex-high-seeded-v2-crm-saas-django | 11 | 8 | 14 | 44.0 | 46.2 |
| python-app | 9 | 5 | 12 | 42.9 | 45.9 |
| vc-claude-code-seeded-v2-healthcare-clinic-django | 17 | 58 | 12 | 58.6 | 44.5 |
| vulnerable-python-apps | 9 | 6 | 13 | 40.9 | 43.7 |
| vc-claude-code-seeded-v2-marketplace-commerce-fastapi | 13 | 8 | 19 | 40.6 | 43.6 |
| vulnpy | 31 | 14 | 49 | 38.8 | 42.5 |
| djangoat | 21 | 34 | 31 | 40.4 | 39.9 |
| vc-kimi-code-seeded-v2-education-lms-django | 11 | 19 | 17 | 39.3 | 38.7 |
| dvpwa | 8 | 7 | 15 | 34.8 | 37.4 |
| pygoat | 28 | 63 | 50 | 35.9 | 34.7 |
| flask-xss | 9 | 10 | 21 | 30.0 | 32.4 |
| vc-kimi-code-seeded-v2-logistics-dispatch-fastapi | 9 | 11 | 22 | 29.0 | 31.3 |
| vc-kimi-code-seeded-v2-healthcare-clinic-django | 9 | 16 | 21 | 30.0 | 31.0 |
| python-insecure-app | 2 | 1 | 6 | 25.0 | 28.6 |
| vc-claude-code-seeded-v2-property-management-fastapi | 8 | 9 | 25 | 24.2 | 26.8 |
| vc-codex-high-seeded-v2-hr-payroll-django | 5 | 6 | 20 | 20.0 | 22.5 |
| damn-vulnerable-flask-application | 3 | 12 | 12 | 20.0 | 20.0 |
| vc-claude-code-seeded-v2-fintech-lending-fastapi | 5 | 6 | 24 | 17.2 | 19.7 |
| vc-claude-code-seeded-v2-logistics-dispatch-fastapi | 5 | 7 | 28 | 15.2 | 17.4 |
| vc-codex-high-seeded-v2-property-management-fastapi | 4 | 8 | 22 | 15.4 | 17.2 |
§
Detection by severity
| Severity | TP | FP | FN | Recall % |
|---|---|---|---|---|
| Critical | 119 | 0 | 36 | 76.8 |
| High | 407 | 2 | 345 | 54.1 |
| Medium | 427 | 1 | 483 | 46.9 |
| Low | 33 | 0 | 53 | 38.4 |
§
Detection by vulnerability class
| CWE family | TP | FP | FN | Recall % |
|---|---|---|---|---|
| Open Redirect | 35 | 0 | 5 | 87.5 |
| Command / OS Injection | 40 | 0 | 10 | 80.0 |
| Code Injection / RFI | 27 | 0 | 7 | 79.4 |
| XML External Entities | 28 | 0 | 10 | 73.7 |
| Insecure Deserialization | 29 | 0 | 11 | 72.5 |
| SQL Injection | 54 | 1 | 24 | 69.2 |
| Server-Side Request Forgery | 25 | 1 | 16 | 61.0 |
| Security Misconfiguration | 66 | 0 | 46 | 58.9 |
| Path Traversal | 24 | 0 | 20 | 54.5 |
| Missing Authentication / Authorization | 43 | 0 | 40 | 51.8 |
| HTTP Header Injection | 1 | 0 | 1 | 50.0 |
| XPath Injection | 2 | 0 | 2 | 50.0 |
| Other | 414 | 0 | 463 | 47.2 |
| Sensitive Data Exposure | 72 | 0 | 83 | 46.5 |
| Hardcoded Credentials | 30 | 0 | 38 | 44.1 |
| Broken Access Control / IDOR | 35 | 1 | 48 | 42.2 |
| Cross-Site Scripting | 46 | 0 | 64 | 41.8 |
| Denial of Service | 15 | 0 | 29 | 34.1 |
§
Cost
Free
Total cost
0
Python LOC scanned
0
Successful runs