Dashboard
Overview · 9 Apr 2026
0% False Positive Rate
Total Scans
48
LLM apps analysed
↑ 12 this month
CVEs Found
347
Across all components
183 proprietary
Critical Issues
24
Requiring action now
↑ 3 since last scan
Components
2,681
Dependencies mapped
100% parse rate

Recent Scans

Last 7 days
🐟
666ghj/BettaFish
SCA · 2h ago · 63 vulnerabilities · Cached
High
🤖
LangChain-RAG-Pipeline v2.1.4
SCA + Pen Test · Yesterday · 312 components
Critical
⚡
OpenAI Agents SDK v1.2.0
SCA + Pen Test · 2 days ago · 94 components
High
🛠️
api4.ai2wj.com (Langflow)
Full Pen Test · 3 days ago · 1 Apr
Medium
🌐
AutoGPT v0.5.1
SCA · 5 days ago · 241 components
Low

Ecosystem Risk

72
Overall Risk Score
24
Critical
67
High
112
Medium
144
Low

Activity

SCA on 666ghj/BettaFish — 63 CVEs found
2 hours ago
Pen test on api4.ai2wj.com — 14 exploits confirmed
1 day ago
AutoGPT v0.5.1 — 241 components parsed, 0 false positives
5 days ago
New Scan
LLM Supply Chain Security Analysis

Scan an LLM Application

Paste a repository URL or upload a project folder. Sentinel will map all components, detect CVEs, and run automated pen testing.

🔬
SCA Scan
Map all LLM components, detect CVEs, 0% false positive
⚔️
Pen Test
Automated agentic pen testing, 660 exploitation tasks
📊
Risk Score
Component-level scoring beyond CVSS for insurance & compliance
Est. 8–12 min · Non-lateral · Zero collateral impact
Scan History
All past scans

Scan History

48 total
🐟
666ghj/BettaFish
SCA · 63 vulnerabilities · 9 Apr 2026 · Cached data
High
🤖
LangChain-RAG-Pipeline v2.1.4
SCA + Pen Test · 312 components · 6 Apr 2026
Critical
🛠️
api4.ai2wj.com (Langflow)
Full Pen Test · 1 Apr 2026
Medium
Scan Results
LangChain-RAG-Pipeline v2.1.4 · 6 Apr 2026
86
LangChain-RAG-Pipeline v2.1.4
SCA + Pen Test · 312 components · 47 CVEs · 14 exploits confirmed
langchain-core 0.1.5 llama-index 0.9.2 transformers 4.36.0
🛡️
47
CVEs found (SCA)
⚔️
14
Exploits confirmed (Pen Test)
📦
312
Components parsed
SCA Results 🔬 SCA
Select a repository to view cached SCA results
0% False Positive Rate
-
Total Vulnerabilities
-
Critical
-
High
-
Medium
🏗️ Architecture Map
🛡️ Vulnerabilities
Select a cached repository to render the architecture map

Architecture Details

Click a component in the graph
← Click a component in the graph

Vulnerability List

Component Ecosystem Severity / CVSS Vulnerability ID PoC Summary
Select a cached repository to view vulnerabilities
Pen Test
LLM-driven Automated Penetration Testing
Non-lateral · Zero Collateral
▶ Live Demo
📘 Summary Report
1
Info Collection
2
Scanning
3
Weakness Gather
4
Attack Decision
5
Exploit & Execute
📋 Penetration Test Summary — api4.ai2wj.com (Langflow v1.2.0)
Target: http://43.156.238.180:7860
Mode: LLM-driven (GPT-4o + Exa + NVD)
Result: Root access confirmed via CVE-2025-57760 + CVE-2025-3248 chain
Exploits confirmed: 14 total · 2 critical chains · RCE as uid=0(root)

Full technical details available in the downloadable .docx report.
Integrations
Connected tools and CI/CD pipelines
GitHub
Auto-scan on push, PR comments with CVE findings
Jira
Auto-create tickets for Critical and High CVEs
Slack
Real-time notifications on scan completion
Docker Hub
Scan container images for embedded LLM dependencies
Rules & Policy
Scan configuration and compliance settings
Scan Rules
Auto-scan on new dependency
Trigger SCA scan when requirements.txt changes
Block deploy on Critical CVE
Fail CI/CD pipeline if any Critical CVE detected
Non-lateral pen test mode
No lateral movement — required for government clients
Compliance Framework
Singapore CSA Framework
Map findings to CSA guidelines
OWASP LLM Top 10
Align pen test findings to OWASP taxonomy
MAS TRMG Alignment
Tag CVEs relevant to MAS guidelines
PoC
Dependency