Scanner deep-dive
Kimi K2.7 by Moonshot AI ↗
General-Purpose LLM · agentic-v1 · scored on 66/66 repositories. Strict scoring (unfinished repos counted as misses).
52.1
F3 (strict)
53.4
F2 (strict)
50.8%
Recall (strict)
67.6%
Precision
66/66
Repos scored
kimi-k2.7-code
Model
$26
Total cost
311s
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 |
|---|---|---|---|---|---|
| vfapi | 8 | 3 | 1 | 92.6 | 88.4 |
| python-app | 16 | 3 | 5 | 76.2 | 77.4 |
| dsvw | 19 | 2 | 8 | 71.6 | 74.5 |
| insecure-web | 7 | 3 | 2 | 74.1 | 72.9 |
| vulnerable-api | 10 | 1 | 4 | 69.0 | 72.3 |
| dsvpwa | 22 | 4 | 10 | 69.8 | 72.2 |
| dvblab | 15 | 3 | 7 | 69.7 | 71.9 |
| vampi | 11 | 4 | 4 | 71.1 | 71.5 |
| damn-vulnerable-flask-application | 10 | 4 | 5 | 64.4 | 65.8 |
| vulnerable-flask-app | 14 | 14 | 7 | 68.2 | 64.0 |
| intentionally-vulnerable-python-application | 4 | 2 | 3 | 61.9 | 62.9 |
| vc-kimi-code-seeded-v2-legal-case-django | 16 | 10 | 10 | 62.8 | 62.7 |
| vc-kimi-code-seeded-v2-marketplace-commerce-fastapi | 16 | 6 | 11 | 59.3 | 61.5 |
| vc-codex-high-seeded-v2-logistics-dispatch-fastapi | 17 | 6 | 12 | 58.6 | 61.2 |
| owasp-web-playground | 17 | 8 | 11 | 59.5 | 61.0 |
| vc-claude-code-seeded-v2-fintech-lending-fastapi | 17 | 6 | 12 | 58.6 | 61.0 |
| vulnerable-tornado-app | 8 | 2 | 6 | 57.1 | 60.3 |
| vc-codex-high-seeded-v2-fintech-lending-fastapi | 17 | 7 | 12 | 57.5 | 59.8 |
| vc-codex-high-seeded-v2-property-management-fastapi | 15 | 6 | 11 | 56.4 | 58.9 |
| lets-be-bad-guys | 13 | 4 | 11 | 55.5 | 58.5 |
| threatbyte | 15 | 7 | 11 | 56.4 | 58.4 |
| dvpwa | 13 | 10 | 10 | 58.0 | 58.0 |
| extremely-vulnerable-flask-app | 17 | 5 | 15 | 54.2 | 57.7 |
| vc-codex-high-seeded-v2-hr-payroll-django | 14 | 7 | 11 | 54.7 | 56.5 |
| vc-claude-code-seeded-v2-logistics-dispatch-fastapi | 18 | 7 | 15 | 53.5 | 56.2 |
| vc-codex-high-seeded-v2-education-lms-django | 14 | 8 | 11 | 54.7 | 56.1 |
| vc-codex-high-seeded-v2-marketplace-commerce-fastapi | 13 | 6 | 12 | 53.3 | 55.9 |
| vc-codex-high-seeded-v2-support-desk-fastapi | 15 | 7 | 13 | 53.6 | 55.9 |
| pythonssti | 1 | 0 | 1 | 50.0 | 55.6 |
| vc-codex-seeded-v2-hr-payroll-django | 20 | 4 | 19 | 50.4 | 54.9 |
| vc-codex-seeded-v2-logistics-dispatch-fastapi | 16 | 6 | 14 | 51.7 | 54.7 |
| vc-kimi-code-seeded-v2-hr-payroll-django | 16 | 11 | 13 | 54.0 | 54.7 |
| vc-kimi-code-seeded-v2-logistics-dispatch-fastapi | 17 | 14 | 14 | 53.8 | 53.8 |
| pygoat | 40 | 24 | 38 | 51.7 | 53.5 |
| vc-claude-code-seeded-v2-legal-case-django | 15 | 7 | 16 | 49.5 | 52.4 |
| vc-codex-seeded-v2-marketplace-commerce-fastapi | 15 | 9 | 14 | 50.6 | 52.4 |
| vc-codex-high-seeded-v2-legal-case-django | 12 | 4 | 13 | 48.0 | 51.5 |
| vc-codex-seeded-v2-property-management-fastapi | 15 | 7 | 16 | 48.4 | 51.5 |
| vc-codex-seeded-v2-fintech-lending-fastapi | 18 | 7 | 19 | 47.8 | 51.2 |
| vc-kimi-code-seeded-v2-fintech-lending-fastapi | 16 | 5 | 17 | 47.5 | 51.2 |
| vc-claude-code-seeded-v2-property-management-fastapi | 16 | 6 | 17 | 47.5 | 50.9 |
| damn-vulnerable-graphql-application | 19 | 25 | 17 | 52.8 | 50.5 |
| vc-codex-high-seeded-v2-crm-saas-django | 12 | 8 | 13 | 48.0 | 50.1 |
| vulnpy | 37 | 8 | 43 | 45.8 | 49.9 |
| vulpy | 26 | 8 | 31 | 45.6 | 49.5 |
| vc-claude-code-seeded-v2-healthcare-clinic-django | 14 | 12 | 15 | 48.3 | 49.3 |
| vc-claude-code-seeded-v2-crm-saas-django | 13 | 8 | 15 | 46.4 | 49.0 |
| vc-claude-code-seeded-v2-support-desk-fastapi | 15 | 6 | 19 | 45.1 | 48.7 |
| vc-claude-code-seeded-v2-education-lms-django | 14 | 5 | 18 | 44.8 | 48.6 |
| vc-claude-code-seeded-v2-hr-payroll-django | 12 | 4 | 15 | 44.4 | 48.4 |
| vc-codex-seeded-v2-legal-case-django | 14 | 4 | 18 | 43.9 | 48.1 |
| vc-codex-seeded-v2-crm-saas-django | 15 | 10 | 19 | 45.1 | 47.4 |
| flask-xss | 13 | 9 | 17 | 44.4 | 46.9 |
| vc-codex-seeded-v2-support-desk-fastapi | 13 | 6 | 17 | 43.3 | 46.8 |
| vulnerable-python-apps | 10 | 5 | 12 | 43.9 | 46.7 |
| python-insecure-app | 3 | 1 | 5 | 41.7 | 46.2 |
| vc-kimi-code-seeded-v2-support-desk-fastapi | 12 | 6 | 16 | 42.9 | 46.1 |
| vc-kimi-code-seeded-v2-crm-saas-django | 12 | 14 | 15 | 45.7 | 45.8 |
| vc-claude-code-seeded-v2-marketplace-commerce-fastapi | 13 | 6 | 19 | 41.7 | 45.3 |
| vc-kimi-code-seeded-v2-education-lms-django | 13 | 17 | 15 | 45.2 | 44.6 |
| vc-codex-seeded-v2-healthcare-clinic-django | 16 | 5 | 25 | 39.8 | 44.1 |
| vc-kimi-code-seeded-v2-healthcare-clinic-django | 12 | 8 | 18 | 41.1 | 44.0 |
| vc-codex-high-seeded-v2-healthcare-clinic-django | 10 | 6 | 16 | 39.7 | 42.9 |
| vc-kimi-code-seeded-v2-property-management-fastapi | 12 | 5 | 18 | 38.9 | 42.0 |
| djangoat | 18 | 14 | 34 | 34.6 | 37.1 |
| vc-codex-seeded-v2-education-lms-django | 10 | 4 | 25 | 28.6 | 32.5 |
§
Detection by severity
| Severity | TP | FP | FN | Recall % |
|---|---|---|---|---|
| Critical | 140 | 0 | 15 | 90.3 |
| High | 419 | 1 | 333 | 55.7 |
| Medium | 391 | 4 | 519 | 43.0 |
| Low | 33 | 0 | 53 | 38.4 |
§
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 |
| SQL Injection | 72 | 0 | 6 | 92.3 |
| Command / OS Injection | 46 | 0 | 4 | 92.0 |
| Code Injection / RFI | 31 | 0 | 3 | 91.2 |
| XML External Entities | 34 | 1 | 4 | 89.5 |
| Path Traversal | 38 | 0 | 6 | 86.4 |
| Server-Side Request Forgery | 35 | 1 | 6 | 85.4 |
| Insecure Deserialization | 34 | 0 | 6 | 85.0 |
| Cross-Site Scripting | 82 | 0 | 28 | 74.5 |
| Hardcoded Credentials | 48 | 1 | 20 | 70.6 |
| Sensitive Data Exposure | 91 | 0 | 64 | 58.7 |
| Security Misconfiguration | 57 | 0 | 55 | 50.9 |
| Missing Authentication / Authorization | 33 | 1 | 50 | 39.8 |
| Other | 305 | 1 | 572 | 34.8 |
| Broken Access Control / IDOR | 23 | 0 | 60 | 27.7 |
| Denial of Service | 12 | 0 | 32 | 27.3 |
| XPath Injection | 1 | 0 | 3 | 25.0 |
§
LLM operational metrics
60,671
Avg input tokens
17,854
Avg output tokens
508,181
Avg total tokens
311s
Avg latency / repo
4.5%
JSON repair rate
198
Total runs
±10.1
F2 run-to-run σ
§
Cost
$26
Total cost
$0.14
Cost / run
$0.007
Cost / 100 LOC
133,782
Python LOC scanned
187
Successful runs