Skip to content

IoTcube-AIbom/T3-AI-Agent-Vulnerability-Detection

Repository files navigation

AI Agent Vulnerability Detection

This repository currently focuses on a narrow task: sharing public benchmark materials and fetch instructions for agent-security evaluation resources.

Shared Resources

  • RAGDefender: https://github.com/SecAI-Lab/RAGDefender.git
  • ASB: https://github.com/agiresearch/ASB.git
  • Benchmark registry: benchmarks/manifest.json
  • Benchmark notes: benchmarks/README.md
  • Dataset notes: datasets/README.md

The upstream codebases are not vendored here. Fetch them on demand:

./scripts/fetch_benchmarks.sh

What Is Kept In This Repo

  • benchmarks/: checkout targets and provenance metadata
  • datasets/: short dataset registry for fetched benchmark assets
  • scripts/fetch_benchmarks.sh: fetch helper for public benchmark repos
  • scripts/verify_resources.sh: lightweight repository/resource check

Other older paths are kept only as compatibility placeholders.

Benchmark Checkouts

  • benchmarks/rag/RAGDefender
  • benchmarks/agent/ASB

Compatibility Placeholders

The older local template scripts are still present, but intentionally minimal:

./scripts/run_local.sh --input-dir ./examples/input --output ./out/output.json
./scripts/validate_schema.sh ./out/output.json
./scripts/smoke_test.sh

Docs

  • docs/getting-started.md
  • docs/input-output-spec.md
  • docs/examples.md
  • docs/configuration.md

About

Scenario-Based Vulnerability Detection for Agentic AI Systems

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages