github.com (opens in a new tab)· Hosted on GitHub

What AI says about AgentDojo

AgentDojo is an evaluation framework for testing LLM agents against prompt injection attacks, data exfiltration, and remote code execution vulnerabilities.

Since Jul 5Updated Nov 20, 2026Based on 4,668 AI answersReviewed by

How we measure

Mentioned in · Public index

<1%

of AI answers about AgentDojo and its rivals · since Jul 5

Based on 4,668 AI answers

  • ChatGPT<1%
  • Google AI Mode<1%

How often AI mentions AgentDojo

Share of AI answers about AgentDojo and its rivals

Track your brand free to see 13 weeks of history.
Use the left and right arrow keys to read each date.
Sep 21OctNov 9
  • · ChatGPT switched to GPT-6 Luna

Key takeaways for AgentDojo

  • Engine split

    ChatGPT (<1%) and Google AI Mode (<1%) mention AgentDojo at similar rates.

  • Strongest market

    AgentDojo ranks #114 in AI Red Teaming & Pen Testing (1%). View AI Red Teaming & Pen Testing

Markets where AI mentions AgentDojo

All marketsChatGPTGoogle AI Mode

Topics where AI mentions AgentDojo

TopicMentioned in · on this topic

AgentDojo in AI answers

1 of 4

How do we test our AI app for prompt injection and jailbreak risks?

ChatGPTChatGPT· Aug 14, 2026
NIST's AgentDojo-based work is useful if your application is an agent that operates on email, web pages, files, or other external data.
Google AI ModeGoogle AI Mode· Sep 23, 2026
Frameworks like AgentDojo or benchmarks tracking agentic tool-use safety can simulate these multi-step exploitation trajectories.

AgentDojo: common questions

Does AI recommend AgentDojo?
AI mentions AgentDojo in <1% of tracked answers across ChatGPT and Google AI Mode. ChatGPT mentions AgentDojo in <1% of answers and Google AI Mode in <1%.
Who are AgentDojo's main competitors in AI answers?
AI most often compares or mentions AgentDojo alongside Promptfoo, NVIDIA Garak, HiddenLayer and PyRIT, including in AI Red Teaming & Pen Testing.
Which sources does AI cite for AgentDojo?
The websites AI cites most often in answers naming AgentDojo include arxiv.org and agentdojo.spylab.ai.
For agents: this page as Markdown, parse.gl/brands/github-com-666.md.

This page

Reuse: Figures and tables on this page are free to republish with attribution: a link to https://parse.gl/brands/github-com-666 beside them. A standard followed link (dofollow) is preferred.

Read and search

This brand's shares and rivals, with 95% ranges: GET agent.parse.gl/v1/tools/check_brand?subject=brd_321af888-9759-4d17-a700-fd370fb5bed3
Search brands: GET parse.gl/api/public/search?q=<words>

Connect

Connect an assistant: agent.parse.gl/mcp

An agent can save work before signup: POST https://agent.parse.gl/v1/workspaces

What it costs

No account: Public figures and up to 5 examples per list, about 120 brands a day per address.
Free account: $5 in credit, your brand's first check (20 buyer questions) and a free weekly check.
After your first top-up: Exports and deeper search results. The first top-up starts at $5.
Live checks: $0.01 per question per engine ($0.05 on Gemini and Claude).
Full public answers and pages: 25 free per day, then $0.005 each.
Public answers older than 90 days: $0.001 each the first time your workspace counts or lists one, then yours.