
agentdojo
by ethz-spylab (organization)
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents. (description from the project’s GitHub page)
Repository facts
- Stars
- 930
- Forks
- 252
- Open issues and pull requests
- 80
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- ethz-spylab · Organization
- Created
- Feb 29, 2024
- Last push
- Jun 2, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 3,571: uber/ADR
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
2,064 starsPythonApache-2.0Last push Oct 16, 2026
Rank 1,180: Tencent/AI-Infra-Guard
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
6,903 starsPythonApache-2.0Last push Oct 17, 2026
Rank 6,396: hashgraph-online/hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
930 starsPythonApache-2.0Last push Oct 18, 2026
Rank 9,441: deadbits/vigil-llm
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
506 starsPythonApache-2.0Last push Jan 31, 2024
Rank 1,196: superagent-ai/superagent
Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.
6,766 starsTypeScriptMITLast push Aug 25, 2026
Rank 6,367: pipelab-org/pipelock
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits media…
937 starsGoApache-2.0Last push Oct 18, 2026