# ottosulin/awesome-ai-security

A collection of awesome resources related AI security

Repository: https://github.com/ottosulin/awesome-ai-security
Canonical: https://ross.abutalabs.com/products/ottosulin-awesome-ai-security
License: MIT
License Family: permissive
Last push: 2026-08-23T06:01:54+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 84
- inputs: {"age_days": 1177, "days_push": 10, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1427, forks 376 (observed 2026-08-28T04:04:41.455146+00:00)

## What it is
A curated awesome list of AI security resources including frameworks, standards, learning materials, and open-source tools. It covers topics like LLM red teaming, guardrails, MCP security, and adversarial ML.

## Use cases
- find resources on securing LLM applications
- learn about AI red teaming techniques
- discover tools for scanning ML models for vulnerabilities
- study OWASP AI security standards
- find guardrail tools for GenAI apps
- research agentic AI and MCP attack vectors

## When to choose
- you need a starting point to explore AI/LLM security topics
- you want curated links to standards, courses, and open-source tools
- you are building a security program for GenAI or agentic systems

## When to avoid
- you need a runnable tool rather than a list of links
- you need in-depth original content instead of curated references
- you need non-security AI learning resources

## Facets
- artifact type: learning-resource
- maturity: active
- function: security, developer-tools
- domain: artificial-intelligence, security, large-language-models, awesome-lists
- platform: -
- tags: awesome-list, ai-security, llm-security, red-teaming, curated-resources, web-server

## Member repositories
- ottosulin/awesome-ai-security (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:41.455146+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:37:23.302132+00:00, confidence not recorded.
  - readme: https://github.com/ottosulin/awesome-ai-security (fetched 2026-08-28T04:04:41.455146+00:00, sha 5588d2230109)
- Data as of 2026-08-30T08:39:29.467469+00:00.