Scanner deep-dive
Kolega Scan OSS - V1 - 2 Model by Kolega Scan OSS ↗
Security-Specialized · Kolega Scan OSS · scored on 66/66 repositories. Strict scoring (unfinished repos counted as misses).
65.2
F3 (strict)
61.9
F2 (strict)
68.8%
Recall (strict)
44.0%
Precision
66/66
Repos scored
twin-distill-flash-dsonly
Model
$22
Total cost
0s
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 |
|---|---|---|---|---|---|
| dsvw | 25 | 13 | 2 | 92.6 | 85.6 |
| dsvpwa | 28 | 16 | 4 | 87.5 | 81.4 |
| dvblab | 20 | 15 | 2 | 90.9 | 81.3 |
| vc-codex-seeded-v2-healthcare-clinic-django | 35 | 19 | 6 | 85.4 | 80.3 |
| vulnerable-tornado-app | 13 | 14 | 1 | 92.9 | 78.3 |
| pythonssti | 2 | 3 | 0 | 100.0 | 76.9 |
| vc-codex-high-seeded-v2-support-desk-fastapi | 24 | 21 | 4 | 85.7 | 76.4 |
| vc-claude-code-seeded-v2-support-desk-fastapi | 28 | 20 | 6 | 82.3 | 76.1 |
| vc-kimi-code-seeded-v2-fintech-lending-fastapi | 28 | 27 | 5 | 84.9 | 74.9 |
| lets-be-bad-guys | 19 | 13 | 5 | 79.2 | 74.2 |
| vc-codex-seeded-v2-logistics-dispatch-fastapi | 24 | 20 | 6 | 80.0 | 73.2 |
| vfapi | 8 | 12 | 1 | 88.9 | 71.4 |
| owasp-web-playground | 21 | 15 | 7 | 75.0 | 70.9 |
| vc-codex-seeded-v2-support-desk-fastapi | 24 | 26 | 6 | 80.0 | 70.6 |
| vc-codex-high-seeded-v2-marketplace-commerce-fastapi | 20 | 22 | 5 | 80.0 | 70.4 |
| insecure-web | 8 | 13 | 1 | 88.9 | 70.2 |
| vc-claude-code-seeded-v2-fintech-lending-fastapi | 24 | 31 | 5 | 82.8 | 70.2 |
| vc-codex-seeded-v2-hr-payroll-django | 31 | 34 | 8 | 79.5 | 70.1 |
| vulnerable-api | 11 | 12 | 3 | 78.6 | 69.6 |
| vc-codex-high-seeded-v2-healthcare-clinic-django | 20 | 21 | 6 | 76.9 | 69.0 |
| vc-claude-code-seeded-v2-property-management-fastapi | 25 | 25 | 8 | 75.8 | 68.7 |
| vulnerable-flask-app | 17 | 23 | 4 | 81.0 | 68.5 |
| vc-codex-seeded-v2-fintech-lending-fastapi | 26 | 16 | 11 | 70.3 | 68.4 |
| vc-codex-seeded-v2-education-lms-django | 25 | 18 | 10 | 71.4 | 68.3 |
| vc-kimi-code-seeded-v2-support-desk-fastapi | 22 | 28 | 6 | 78.6 | 67.9 |
| vc-codex-seeded-v2-marketplace-commerce-fastapi | 22 | 25 | 7 | 75.9 | 67.5 |
| threatbyte | 19 | 18 | 7 | 73.1 | 67.4 |
| extremely-vulnerable-flask-app | 22 | 16 | 10 | 68.8 | 66.3 |
| vc-codex-high-seeded-v2-property-management-fastapi | 20 | 27 | 6 | 76.9 | 66.2 |
| damn-vulnerable-flask-application | 12 | 19 | 3 | 80.0 | 65.9 |
| vc-codex-high-seeded-v2-fintech-lending-fastapi | 22 | 29 | 7 | 75.9 | 65.9 |
| vc-codex-high-seeded-v2-crm-saas-django | 21 | 40 | 4 | 84.0 | 65.2 |
| vc-claude-code-seeded-v2-crm-saas-django | 21 | 29 | 7 | 75.0 | 64.8 |
| vc-claude-code-seeded-v2-marketplace-commerce-fastapi | 23 | 28 | 9 | 71.9 | 64.2 |
| vc-codex-seeded-v2-property-management-fastapi | 20 | 14 | 11 | 64.5 | 63.3 |
| vc-codex-seeded-v2-crm-saas-django | 23 | 27 | 11 | 67.7 | 61.8 |
| vc-kimi-code-seeded-v2-crm-saas-django | 20 | 35 | 7 | 74.1 | 61.3 |
| vc-kimi-code-seeded-v2-legal-case-django | 20 | 39 | 6 | 76.9 | 61.3 |
| vc-claude-code-seeded-v2-hr-payroll-django | 17 | 15 | 10 | 63.0 | 60.7 |
| vc-kimi-code-seeded-v2-education-lms-django | 20 | 33 | 8 | 71.4 | 60.6 |
| python-app | 17 | 40 | 4 | 81.0 | 60.3 |
| vc-kimi-code-seeded-v2-logistics-dispatch-fastapi | 23 | 46 | 8 | 74.2 | 59.6 |
| vc-codex-seeded-v2-legal-case-django | 22 | 31 | 11 | 66.7 | 59.5 |
| vc-claude-code-seeded-v2-legal-case-django | 20 | 26 | 11 | 64.5 | 58.8 |
| dvpwa | 15 | 21 | 8 | 65.2 | 58.6 |
| vc-kimi-code-seeded-v2-marketplace-commerce-fastapi | 18 | 29 | 9 | 66.7 | 58.1 |
| vc-claude-code-seeded-v2-education-lms-django | 20 | 25 | 12 | 62.5 | 57.8 |
| vc-claude-code-seeded-v2-logistics-dispatch-fastapi | 20 | 21 | 13 | 60.6 | 57.8 |
| vc-kimi-code-seeded-v2-healthcare-clinic-django | 20 | 33 | 10 | 66.7 | 57.8 |
| intentionally-vulnerable-python-application | 6 | 18 | 1 | 85.7 | 57.7 |
| pygoat | 46 | 41 | 32 | 59.0 | 57.6 |
| damn-vulnerable-graphql-application | 21 | 21 | 15 | 58.3 | 56.5 |
| vc-codex-high-seeded-v2-education-lms-django | 17 | 34 | 8 | 68.0 | 56.3 |
| vampi | 10 | 19 | 5 | 66.7 | 56.2 |
| vc-kimi-code-seeded-v2-hr-payroll-django | 19 | 40 | 10 | 65.5 | 54.3 |
| vc-codex-high-seeded-v2-hr-payroll-django | 16 | 35 | 9 | 64.0 | 53.0 |
| vc-codex-high-seeded-v2-logistics-dispatch-fastapi | 17 | 34 | 12 | 58.6 | 50.9 |
| vc-claude-code-seeded-v2-healthcare-clinic-django | 16 | 26 | 13 | 55.2 | 50.6 |
| vc-kimi-code-seeded-v2-property-management-fastapi | 18 | 55 | 12 | 60.0 | 46.6 |
| djangoat | 24 | 29 | 28 | 46.2 | 46.0 |
| vc-codex-high-seeded-v2-legal-case-django | 14 | 40 | 11 | 56.0 | 45.5 |
| flask-xss | 13 | 18 | 17 | 43.3 | 43.0 |
| vulnerable-python-apps | 11 | 29 | 11 | 50.0 | 43.0 |
| vulpy | 23 | 35 | 34 | 40.4 | 40.2 |
| vulnpy | 31 | 44 | 49 | 38.8 | 39.2 |
| python-insecure-app | 3 | 7 | 5 | 37.5 | 35.7 |
§
Detection by severity
| Severity | TP | FP | FN | Recall % |
|---|---|---|---|---|
| Critical | 138 | 0 | 17 | 89.0 |
| High | 529 | 7 | 223 | 70.3 |
| Medium | 598 | 5 | 312 | 65.7 |
| Low | 45 | 1 | 41 | 52.3 |
§
Detection by vulnerability class
| CWE family | TP | FP | FN | Recall % |
|---|---|---|---|---|
| HTTP Header Injection | 2 | 0 | 0 | 100.0 |
| Open Redirect | 39 | 0 | 1 | 97.5 |
| Command / OS Injection | 46 | 0 | 4 | 92.0 |
| Code Injection / RFI | 30 | 0 | 4 | 88.2 |
| XML External Entities | 33 | 1 | 5 | 86.8 |
| SQL Injection | 63 | 1 | 15 | 80.8 |
| Path Traversal | 35 | 1 | 9 | 79.5 |
| Security Misconfiguration | 88 | 0 | 24 | 78.6 |
| Insecure Deserialization | 30 | 0 | 10 | 75.0 |
| Cross-Site Scripting | 80 | 0 | 30 | 72.7 |
| Hardcoded Credentials | 47 | 0 | 21 | 69.1 |
| Server-Side Request Forgery | 27 | 2 | 14 | 65.9 |
| Other | 577 | 3 | 300 | 65.8 |
| Sensitive Data Exposure | 95 | 0 | 60 | 61.3 |
| Broken Access Control / IDOR | 50 | 3 | 33 | 60.2 |
| Missing Authentication / Authorization | 49 | 2 | 34 | 59.0 |
| XPath Injection | 2 | 0 | 2 | 50.0 |
| Denial of Service | 17 | 0 | 27 | 38.6 |
§
LLM operational metrics
0
Avg input tokens
0
Avg output tokens
0
Avg total tokens
0s
Avg latency / repo
0.0%
JSON repair rate
66
Total runs
§
Cost
$22
Total cost
$0.34
Cost / run
$0.017
Cost / 100 LOC
133,782
Python LOC scanned
66
Successful runs