# corca-ai/awesome-llm-security

A curation of awesome tools, documents and projects about LLM Security.

Repository: https://github.com/corca-ai/awesome-llm-security
Canonical: https://ross.abutalabs.com/products/awesome-llm-security
License Family: other
Topics: awesome, awesome-list, llm, security
Last push: 2025-08-20T01:27:47+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 37, release rhythm 35, longevity 82
- inputs: {"age_days": 1155, "days_push": 379, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1686, forks 335 (observed 2026-08-28T04:05:22.142523+00:00)

## What it is
A curated awesome-list of tools, papers, benchmarks, and articles focused on LLM security, covering attacks like jailbreaks and prompt injection as well as defenses. It serves as a research navigation resource rather than runnable software.

## Use cases
- find research papers on LLM jailbreak attacks
- learn about prompt injection techniques and defenses
- discover benchmarks for LLM security testing
- research adversarial attacks on large language models
- find tools for securing LLM-integrated applications
- survey the state of LLM security research

## When to choose
- you need a starting point for LLM security research
- you want a curated index of papers, tools, and benchmarks on LLM attacks and defenses

## When to avoid
- you need a runnable security tool rather than a reference list
- you need production security controls for your LLM application

## Facets
- artifact type: learning-resource
- maturity: active
- function: security, developer-tools
- domain: large-language-models, security, artificial-intelligence, awesome-lists
- platform: cross-platform
- tags: awesome-list, llm-security, prompt-injection, jailbreak, adversarial-attacks, curated-resources

## Member repositories
- corca-ai/awesome-llm-security (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:22.142523+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 2026-08-30T03:38:56.545957+00:00, confidence not recorded.
  - readme: https://github.com/corca-ai/awesome-llm-security (fetched 2026-08-28T04:05:22.142523+00:00, sha b2f131487b6c)
- Data as of 2026-08-30T08:39:29.467469+00:00.