REPOGEO REPORT · LITE

greshake/llm-security

Default branch main · commit c312325b · scanned 6/27/2026, 10:48:56 AM

GitHub: 2,102 stars · 153 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

3 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE

35 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

1 pass · 1 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 greshake/llm-security, 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

Reposition README opening to clarify its role as a research/demonstration resource

Why:

CURRENT

## New: Demonstrating Indirect Injection attacks on Bing Chat

COPY-PASTE FIX

## LLM Security: Demonstrations and Research on Indirect Prompt Injection
This repository provides a comprehensive collection of proof-of-concept demonstrations and research findings on LLM security vulnerabilities, with a focus on indirect prompt injection. It serves as an educational resource for security researchers, developers, and practitioners to understand and explore new attack vectors against app-integrated Large Language Models, accompanying our detailed paper on ArXiv.

hightopics#2

Add specific topics to improve categorization

Why:

COPY-PASTE FIX

llm-security, prompt-injection, llm-vulnerabilities, ai-security, large-language-models, security-research, proof-of-concept

mediumhomepage#3
Add a homepage URL linking to the research paper
Why:
COPY-PASTE FIX
```
https://arxiv.org/pdf/2303.06572.pdf
```

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 greshake/llm-security

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

llm-random-walk/garak

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

llm-random-walk/garak · recommended 1×
laiyer-ai/llm-guard · recommended 1×
Lakera Guard · recommended 1×
protectai/rebuff · recommended 1×
Prompt Security · recommended 1×

CATEGORY QUERY
How to identify and mitigate prompt injection vulnerabilities in my AI applications?
you: not recommended
AI recommended (in order):
1. Garak (llm-random-walk/garak)
2. LLM Guard (laiyer-ai/llm-guard)
3. Lakera Guard
4. Rebuff (protectai/rebuff)
5. Prompt Security
6. NeMo Guardrails (NVIDIA/NeMo-Guardrails)
7. LangChain (langchain-ai/langchain)
AI recommended 7 alternatives but never named greshake/llm-security. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What are best practices for securing language models integrated into applications?
you: not recommended
AI recommended (in order):
1. OWASP ESAPI
2. Sanitizer
3. DOMPurify (cure53/DOMPurify)
4. OpenAI Moderation API
5. Google Cloud Content Moderation API
6. Azure Content Moderator
7. Auth0
8. Okta
9. AWS IAM
10. Cloudflare
11. NGINX
12. Kong Gateway (Kong/kong)
13. Presidio (microsoft/presidio)
14. Google Cloud Data Loss Prevention (DLP) API
15. AWS Macie
16. Datadog
17. Prometheus (prometheus/prometheus)
18. Grafana (grafana/grafana)
19. Kubernetes (kubernetes/kubernetes)
20. HashiCorp Vault (hashicorp/vault)
21. Tenable Nessus
AI recommended 21 alternatives but never named greshake/llm-security. This is the gap to close.
Show full AI answer

Objective checks

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

Metadata completeness
warn
Suggestion:
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 greshake/llm-security?
pass
AI named greshake/llm-security explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts greshake/llm-security in production, what risks or prerequisites should they evaluate first?
pass
AI named greshake/llm-security 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 greshake/llm-security solve, and who is the primary audience?
pass
AI named greshake/llm-security 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 greshake/llm-security. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/greshake/llm-security.svg)](https://repogeo.com/en/r/greshake/llm-security)

HTML

<a href="https://repogeo.com/en/r/greshake/llm-security"><img src="https://repogeo.com/badge/greshake/llm-security.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

greshake/llm-security — 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