---
title: "agentdojo vs chatgpt-plugin-eval"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/ethz-spylab-agentdojo-vs-llm-platform-security-chatgpt-plugin-eval"
tools: ["ethz-spylab-agentdojo", "llm-platform-security-chatgpt-plugin-eval"]
---

# agentdojo vs chatgpt-plugin-eval

*GraphCanon updated Aug 5, 2026*

## Verdict

Pick agentdojo if agentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents; pick chatgpt-plugin-eval if chatgpt-plugin-eval is an evaluation framework designed specifically to assess security, privacy, and safety concerns related to third-party plugins interfacing with large language models like ChatGPT.

[agentdojo](https://agentdojo.spylab.ai/) reports 716 GitHub stars, 188 forks, and 41 open issues, last pushed Jun 2, 2026. [chatgpt-plugin-eval](https://llm-platform-security.github.io/chatgpt-plugin-eval/) has 29 stars, 7 forks, and 1 open issues, last pushed Jul 29, 2024. Figures are from public GitHub metadata via [agentdojo's repository](https://github.com/ethz-spylab/agentdojo) and [chatgpt-plugin-eval's repository](https://github.com/llm-platform-security/chatgpt-plugin-eval).

| | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [chatgpt-plugin-eval](/tools/llm-platform-security-chatgpt-plugin-eval.md) |
| --- | --- | --- |
| Tagline | A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents | Framework for Evaluating Security in LLM Plugin Ecosystems |
| Stars | 716 | 29 |
| Forks | 188 | 7 |
| Open issues | 41 | 1 |
| Language | Python | HTML |
| Adopt for | AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. | chatgpt-plugin-eval is an evaluation framework designed specifically to assess security, privacy, and safety concerns related to third-party plugins interfacing with large language models like ChatGPT. |
| Persona | - | - |
| Runtime | - | - |
| License | MIT | The license information for chatgpt-plugin-eval is unknown. |
| Categories | AI Agents, Evaluation & Observability | Evaluation & Observability |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [chatgpt-plugin-eval](/tools/llm-platform-security-chatgpt-plugin-eval.md) |
| --- | --- | --- |
| Maintenance | Steady (60%) | Dormant (18%) |
| Days since push | 63d | 736d |
| Open issues (now) | 41 | 1 |
| Full report | [trust report](/tools/ethz-spylab-agentdojo/trust.md) | [trust report](/tools/llm-platform-security-chatgpt-plugin-eval/trust.md) |

## Decision facts: agentdojo

- **Pricing:** freemium - Open-source under the MIT License. Some advanced features might require additional libraries or APIs.
- **Requirements:** Min 8 GB RAM
- **Adopt for:** AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.

## Decision facts: chatgpt-plugin-eval

- **Pricing:** freemium
- **Adopt for:** chatgpt-plugin-eval is an evaluation framework designed specifically to assess security, privacy, and safety concerns related to third-party plugins interfacing with large language models like ChatGPT.
- **License detail:** The license information for chatgpt-plugin-eval is unknown.

## Choose when

### Choose agentdojo if…

- agentdojo is primarily Python; chatgpt-plugin-eval is HTML.
- Pricing: Open-source under the MIT License. Some advanced features might require additional libraries or APIs..
- Requirements: Min 8 GB RAM.
- Tags unique to agentdojo: benchmark, large language models, prompt-injection.
- Also covers AI Agents.
- AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.

### Choose chatgpt-plugin-eval if…

- chatgpt-plugin-eval is primarily HTML; agentdojo is Python.
- Tags unique to chatgpt-plugin-eval: chatgpt, llm-plugins, privacy.
- - When evaluating the security risks of integrating third-party services into your LLM platform through plugins

## When NOT to use agentdojo

- AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism.
- Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.

## When NOT to use chatgpt-plugin-eval

- - In cases where only generic, high-level security guidance is required without an in-depth framework analysis
- - When the primary focus is on improving performance metrics rather than addressing specific security and privacy concerns of LLM plugins

## Common questions

### What is the difference between agentdojo and chatgpt-plugin-eval?

agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. chatgpt-plugin-eval: Framework for Evaluating Security in LLM Plugin Ecosystems. See the comparison table for live GitHub stats and shared categories.

### When should I choose agentdojo over chatgpt-plugin-eval?

Choose agentdojo over chatgpt-plugin-eval when agentdojo is primarily Python; chatgpt-plugin-eval is HTML; Pricing: Open-source under the MIT License. Some advanced features might require additional libraries or APIs.; Requirements: Min 8 GB RAM; Tags unique to agentdojo: benchmark, large language models, prompt-injection; Also covers AI Agents; AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.

### When should I choose chatgpt-plugin-eval over agentdojo?

Choose chatgpt-plugin-eval over agentdojo when chatgpt-plugin-eval is primarily HTML; agentdojo is Python; Tags unique to chatgpt-plugin-eval: chatgpt, llm-plugins, privacy; - When evaluating the security risks of integrating third-party services into your LLM platform through plugins.

### When should I avoid agentdojo?

AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.

### When should I avoid chatgpt-plugin-eval?

- In cases where only generic, high-level security guidance is required without an in-depth framework analysis - When the primary focus is on improving performance metrics rather than addressing specific security and privacy concerns of LLM plugins

### Is agentdojo or chatgpt-plugin-eval more popular on GitHub?

agentdojo has more GitHub stars (716 vs 29). Stars measure visibility, not whether either tool fits your constraints.

### Are agentdojo and chatgpt-plugin-eval open source?

Yes - both are open-source projects on GitHub.

### Where can I find alternatives to agentdojo or chatgpt-plugin-eval?

GraphCanon lists graph-backed alternatives at [agentdojo alternatives](/tools/ethz-spylab-agentdojo/alternatives) and [chatgpt-plugin-eval alternatives](/tools/llm-platform-security-chatgpt-plugin-eval/alternatives) ([agentdojo markdown twin](/tools/ethz-spylab-agentdojo/alternatives.md), [chatgpt-plugin-eval markdown twin](/tools/llm-platform-security-chatgpt-plugin-eval/alternatives.md)), ranked by typed relationship edges rather than popularity votes.

### Is there a machine-readable version of this comparison?

Yes. The markdown twin at [this comparison](/compare/ethz-spylab-agentdojo-vs-llm-platform-security-chatgpt-plugin-eval.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

### Which is better maintained, agentdojo or chatgpt-plugin-eval?

agentdojo: Steady. chatgpt-plugin-eval: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.

### Where are the full trust reports for agentdojo and chatgpt-plugin-eval?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agentdojo trust report](/tools/ethz-spylab-agentdojo/trust); [chatgpt-plugin-eval trust report](/tools/llm-platform-security-chatgpt-plugin-eval/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=ethz-spylab-agentdojo`](/api/graphcanon/graph?tool=ethz-spylab-agentdojo)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_