RRepoGEO

REPOGEO REPORT · LITE

ethz-spylab/agentdojo

Default branch main · commit 089ed468 · scanned 6/13/2026, 1:26:46 AM

GitHub: 619 stars · 159 forks

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface ethz-spylab/agentdojo, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Add an introductory paragraph to the README

    Why:

    CURRENT
    The README currently jumps directly from the title and author list to 'Quickstart.'
    COPY-PASTE FIX
    After the title and author list, but before the 'Quickstart' section, add a paragraph such as: 'AgentDojo provides a unique, dynamic environment designed for evaluating LLM agents on complex, multi-step, real-world web-based tasks. It simulates a realistic browser environment, enabling comprehensive assessment of agent robustness against prompt injection attacks and the effectiveness of various defenses.'
  • hightopics#2
    Expand repository topics with more specific security and testing keywords

    Why:

    CURRENT
    benchmark, large-language-models, prompt-injection, security
    COPY-PASTE FIX
    benchmark, large-language-models, prompt-injection, security, adversarial-testing, red-teaming, llm-security, vulnerability-assessment, agent-security
  • mediumreadme#3
    Add a 'Why AgentDojo?' or 'Key Features' section to the README

    Why:

    CURRENT
    There is no explicit section detailing unique features or a comparison to alternatives.
    COPY-PASTE FIX
    Add a new section, for example, 'Why AgentDojo?' or 'Key Features', detailing its unique aspects such as: 'Dynamic, realistic browser environment for agent evaluation', 'Focus on complex, multi-step web-based tasks', and 'Comprehensive evaluation of both prompt injection attacks and defenses for LLM agents.'

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface ethz-spylab/agentdojo
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
LLM Guard
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. LLM Guard · recommended 2×
  2. LangChain · recommended 2×
  3. LlamaIndex · recommended 2×
  4. Garak · recommended 1×
  5. PromptInject · recommended 1×
  • CATEGORY QUERY
    How to benchmark large language model agent robustness against prompt injection vulnerabilities?
    you: not recommended
    AI recommended (in order):
    1. Garak
    2. LLM Guard
    3. PromptInject
    4. Adversarial Robustness Toolbox (ART) by IBM
    5. OWASP LLM Top 10
    6. Trail of Bits
    7. NCC Group
    8. Cure53
    9. LangChain
    10. LlamaIndex

    AI recommended 10 alternatives but never named ethz-spylab/agentdojo. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Need a testing environment to assess LLM agent security against adversarial prompts.
    you: not recommended
    AI recommended (in order):
    1. Giskard
    2. LLM Guard
    3. Gandalf (by Lakera AI)
    4. Adversarial GLUE (AdvGLUE)
    5. OpenAI Evals
    6. Red Teaming Language Models (from Anthropic)
    7. LangChain
    8. LlamaIndex

    AI recommended 8 alternatives but never named ethz-spylab/agentdojo. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of ethz-spylab/agentdojo?
    pass
    AI named ethz-spylab/agentdojo explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts ethz-spylab/agentdojo in production, what risks or prerequisites should they evaluate first?
    pass
    AI named ethz-spylab/agentdojo explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo ethz-spylab/agentdojo solve, and who is the primary audience?
    pass
    AI named ethz-spylab/agentdojo explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of ethz-spylab/agentdojo. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/ethz-spylab/agentdojo.svg)](https://repogeo.com/en/r/ethz-spylab/agentdojo)
HTML
<a href="https://repogeo.com/en/r/ethz-spylab/agentdojo"><img src="https://repogeo.com/badge/ethz-spylab/agentdojo.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

ethz-spylab/agentdojo — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite