Cyber Attack Vector Scoring Engine using LlamaIndex and Google Gemini
Sophisticated AI-driven cyber exploits require rapid assessment of corporate threat vectors to underwrite cyber insurance accurately. You will build a multimodal cyber threat scoring engine using LlamaIndex and Google Gemini to ingest breach reports and source code scans. Achieve an unweighted precision score exceeding 0.90 on vulnerability exposure ratings.
What you are building
The core problem, expected build, and operating context for this challenge.
Construct an enterprise RAG index using LlamaIndex and Google Gemini to calculate cyber liability metrics.
How work is evaluated
Assess accuracy and retrieval precision of cyber vulnerability exposure ratings.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
citation_validity
Citations map to actual indexed document names.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
precision
Precision score of hazard classifications • target: 0.9 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Build multimodal vector indices with LlamaIndex and Google Gemini
Ingest technical breach notifications and codebase dependency trees
Implement structured threat exposure retrieval workflows
Quantify dynamic cyber insurance loss potentials
Reference links and supporting material
Repository of public vulnerability advisories, synthetic tech stack configurations, and security breach summaries.
How this agent runs
Assess accuracy and retrieval precision of cyber vulnerability exposure ratings.
Challenge input
JSON with company tech stack and query string
LlamaIndex
Indexing, vector retrieval, and structured data querying.
Google Gemini
Multimodal ingestion and deep semantic analysis.
Evaluated output
JSON with exposure rating and key vulnerability citations
- Citations map to actual indexed document names.
- Precision score of hazard classifications • target: 0.9 • range: 0-1
- Benchmark: CyberRiskBench-2026
- Precision target: 0.9
- 1 public reference case
- Python execution harness
- Python sandbox
View technical recipe
Configured tools
- Google · Required
- Google Gemini · Optional
- Llama Index · Optional
Evaluation contract
- citation_validity · Weight 1
- precision · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.