RRepoGEO

REPOGEO REPORT · LITE

prompt-security/ps-fuzz

Default branch main · commit a04982f5 · scanned 6/7/2026, 10:06:45 PM

GitHub: 684 stars · 97 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 prompt-security/ps-fuzz, 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
    Strengthen README's opening paragraph with specific use cases

    Why:

    CURRENT
    This interactive tool assesses the security of your GenAI application's system prompt against various dynamic LLM-based attacks.
    COPY-PASTE FIX
    Prompt Fuzzer is an open-source, interactive tool designed to help you test and harden your GenAI application's system prompts against critical security threats like prompt injection and jailbreak vulnerabilities.
  • mediumabout#2
    Clarify tool identity and specific threats in the repository description

    Why:

    CURRENT
    Make your GenAI Apps Safe & Secure :rocket: Test & harden your system prompt
    COPY-PASTE FIX
    Prompt Fuzzer (ps-fuzz) is an open-source tool from Prompt Security to make your GenAI Apps Safe & Secure :rocket: Test & harden your system prompt against prompt injection and jailbreak vulnerabilities.
  • lowtopics#3
    Add more specific security testing topics

    Why:

    CURRENT
    ai, ai-fuzzer, fuzzer, generative-ai, llm, llm-fuzzer, security, security-tools, system-prompt-hardener
    COPY-PASTE FIX
    ai, ai-fuzzer, fuzzer, generative-ai, llm, llm-fuzzer, security, security-tools, system-prompt-hardener, prompt-injection, jailbreak-detection, llm-security-testing

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 prompt-security/ps-fuzz
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. AdvBench · recommended 2×
  3. Giskard · recommended 1×
  4. Lakera Guard · recommended 1×
  5. Prompt Security · recommended 1×
  • CATEGORY QUERY
    How can I test my LLM application for prompt injection and jailbreak vulnerabilities?
    you: not recommended
    AI recommended (in order):
    1. Giskard
    2. Lakera Guard
    3. Prompt Security
    4. Rebuff
    5. LLM Guard
    6. AdvBench
    7. Adversarial Robustness Toolbox (ART)

    AI recommended 7 alternatives but never named prompt-security/ps-fuzz. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What tools help harden system prompts against various generative AI security threats?
    you: not recommended
    AI recommended (in order):
    1. LLM Guard
    2. NeMo Guardrails
    3. OWASP ESAPI
    4. bleach
    5. OpenAI Moderation API
    6. Azure Content Moderator
    7. Microsoft Purview
    8. Symantec DLP
    9. AdvBench
    10. Garak

    AI recommended 10 alternatives but never named prompt-security/ps-fuzz. 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 prompt-security/ps-fuzz?
    pass
    AI named prompt-security/ps-fuzz explicitly

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

  • If a team adopts prompt-security/ps-fuzz in production, what risks or prerequisites should they evaluate first?
    pass
    AI named prompt-security/ps-fuzz 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 prompt-security/ps-fuzz solve, and who is the primary audience?
    pass
    AI named prompt-security/ps-fuzz 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 prompt-security/ps-fuzz. 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/prompt-security/ps-fuzz.svg)](https://repogeo.com/en/r/prompt-security/ps-fuzz)
HTML
<a href="https://repogeo.com/en/r/prompt-security/ps-fuzz"><img src="https://repogeo.com/badge/prompt-security/ps-fuzz.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

prompt-security/ps-fuzz — 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