agentdojo

Framework-native, reproducible prompt-injection benchmark, CI gate, ImpactTwin procurement tests, and attested ProofRun evidence for AI agents.

Action-graded severity scoring (L0-L6) for tool-using AI agents, computed from red-team execution traces.

Benchmarking schema-valid false tool observations and defense baselines for tool-using LLM agents.

A local-first research scaffold for evaluating models, agent harnesses, and complete agent products on realistic, stateful tasks.

Professional AI Agent Security Portfolio - Kaggle AI Agent Security Competition (76.995 score) - Multi-step attacks, WhiteRabbitNeo optimization, AgentDojo red-teaming

LangChain-native AgentDojo benchmark: utility + ASR evaluation across banking, slack, travel, and workspace suites.

Evaluating provenance-gated tool calls as a prompt injection defense on AgentDojo. Reproducible runs, per-case analysis, and published results.

プロンプトインジェクションの評価フレームワークの再現実験

Security audit of LLM-based multi-agent systems with indirect prompt-injection PoCs and mitigations.

Personal research project — solo, unaffiliated. Inspect AI evaluation framework for LLM agent security: ASR, benign utility, and Transparency Rate across prompt injection, tool poisoning, and psych attacks.

Reproducible evaluation of deterministic sequence rules for AI-agent tool-call traces.