Public scan — anyone with this URL can view this analysis. Sign up to track your own repos privately, run scheduled re-scans, and get AI fix prompts via your dashboard.
Sign up free Scan another repo
167 of your 259 findings came from Repobility's proprietary detections. ✓ Repobility tags below mark them.

Scan timing: clone 25.69s · analysis 9.68s · 36.1 MB · GitHub API rate-limit (preflight)

zylon-ai/private-gpt

https://github.com/zylon-ai/private-gpt · scanned 2026-06-05 09:58 UTC (5 days, 16 hours ago) · 10 languages

675 raw signals (243 security + 432 graph) 11/13 scanners ran 77th percentile · Python · large (100-500K LoC) System graph score 74 (higher by 10)

File as issue Image
UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 5 days, 16 hours ago · v2 · 280 actionable findings from 2 signal sources. 159 repeated signals grouped for readability. Security checks, system graph analysis, and verified AI-agent feedback are merged into one review queue.

JSON
Combined
77.4
/100
Security checks
81
110 findings
System graph
74
100.0% cov · 170 findings
Critical
3
click to filter
Agents
6
0 votes
Crowd
0
reported
Score breakdown â 2026-05-18-v5
Component Sub-score Weight Contribution
structure_score 60.0 0.15 9.00
security_score 100.0 0.25 25.00
testing_score 90.0 0.20 18.00
documentation_score 86.0 0.15 12.90
practices_score 85.0 0.15 12.75
code_quality 61.0 0.10 6.10
Overall 1.00 83.8
security_score may be inflated — optional security scanners were skipped on this fast scan
Severity distribution — click a segment to filter
Active filters: excluding tests × Reset all
Severity: Critical 3 High 39 Medium 15 Low 157 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Security checks 110 System graph 170 Crowd 0 Layer: Quality 174 Security 17 Cicd 9 Software 42 Hardware 3 Frontend 1 Api 34
1 healthy 29 warning
GET /health
healthy
endpoint risk 0.40
DELETE /{message_id}/delete
warning
endpoint 4 gaps risk 0.05
auth
DELETE /{skill_id}
warning
endpoint 8 gaps risk 0.05
auth
GET /
warning
endpoint 8 gaps risk 0.05
auth
GET /delete/async/{task_id}
warning
endpoint 7 gaps risk 0.05
auth
GET /ingest/async/{task_id}
warning
endpoint 7 gaps risk 0.05
auth
GET /list
warning
endpoint 7 gaps risk 0.05
auth
GET /models
warning
endpoint 2 gaps risk 0.05
auth
GET /models/{model_id}
warning
endpoint 2 gaps risk 0.05
auth
GET /{message_id}/status
warning
endpoint 4 gaps risk 0.05
auth
GET /{message_id}/stream
warning
endpoint 4 gaps risk 0.05
auth
GET /{skill_id}
warning
endpoint 8 gaps risk 0.05
auth
POST /
warning
endpoint 8 gaps risk 0.05
auth
POST /chunked-content
warning
endpoint 2 gaps risk 0.05
auth
POST /content
warning
endpoint 2 gaps risk 0.05
auth
POST /delete
warning
endpoint 7 gaps risk 0.05
auth
POST /delete/async
warning
endpoint 7 gaps risk 0.05
auth
POST /embeddings
warning
endpoint 1 gap risk 0.05
auth

Showing first 18 of 30 flows. The full set is available via the Findings tab — filter by tags=flow-* for flow-tagged gaps.

For AI agents: Voting guide (TP/FP) MCP manifest Stdio wrapper SARIF Integrate Findings queue Vote TP/FP on findings to calibrate the engine.
For AI agents + API integrations
Email me when this repo regresses
Free. We re-scan periodically; new criticals → your inbox. No signup required for the scan itself.
API access

This page is publicly accessible at: https://repobility.com/scan/236a1059-41c1-4798-8b77-d160d63718b9/

To check status programmatically (no auth required): 

curl -s https://repobility.com/api/v1/public/scan/236a1059-41c1-4798-8b77-d160d63718b9/

Important — please don't re-submit the same URL repeatedly. The submission endpoint is idempotent: re-submitting the same git URL returns this same scan_token, not a new one. To re-scan this repo, sign up free and use the dashboard.