Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/PurpleLlama
Library/PurpleLlamaForked

meta-llama/PurpleLlama

PurpleLlama

Set of tools to assess and improve LLM security.

View on GitHub↗Upstream meta-llama/PurpleLlama↗

Builder

Meta

Meta

meta-llama • big-tech

Stars

4,292

Using upstream star count

Forks

752

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Dec 6, 2023

Project creation date

README Summary

<p align="center"> <img src="https://github.com/facebookresearch/PurpleLlama/blob/main/logo.png" width="400"/> </p>

Community Evaluation

Loading…

AI Dev Skills

Unmapped

Adversarial TestingAI Risk MitigationAI Safety EngineeringContent FilteringCybersecurity EvaluationLLM Red TeamingLLM Security AssessmentLLM Vulnerability AssessmentPrompt Injection DetectionSafety Benchmarking

Tags

Adversarial TestingAI Risk MitigationAI Safety EngineeringContent FilteringCybersecurity EvaluationLLM Red TeamingLLM Security AssessmentLLM Vulnerability AssessmentPrompt Injection DetectionSafety BenchmarkingAI AgentsBenchmarkingContext EngineeringEvalsForkedHuggingFaceJupyterLarge Language ModelsLlamaPrompt InjectionRed TeamingSecurityTutorial

Taxonomy

AI Trends

AI SafetyLLM SecurityAI GovernanceResponsible AIAI Risk ManagementRed Teaming AI

category

Evals & BenchmarkingFoundation ModelsAI AgentsDev Tools & AutomationLearning ResourcesSecurity & SafetyData Science & Analytics

Deployment Context

Self-hostedOn-premiseCloud API

Industries

CybersecurityFinTechHealthcareLegal TechEnterprise SoftwareGovernmentDefense

Modalities

TextCode

Skill Areas

LLM Security AssessmentAI Safety EngineeringCybersecurity EvaluationPrompt Injection DetectionLLM Red TeamingAI Risk MitigationSafety BenchmarkingAdversarial TestingContent FilteringLLM Vulnerability Assessment

tag

AI AgentsBenchmarkingContext EngineeringEvalsForkedHuggingFaceJupyterLarge Language ModelsLlamaPrompt InjectionRed TeamingSecurityTutorial

Use Cases

LLM Security AuditingPrompt Injection PreventionUnsafe Content DetectionAI System Penetration TestingLLM Safety BenchmarkingSecurity Compliance AssessmentAI Red Team OperationsVulnerability Scanning for AI Systems

Recent Activity

Updated 4 months ago

7 Days

0

30 Days

0

90 Days

0

Fix RCE for canary exploit

Daniel Song • Mar 11, 2026

48fa920

Update minimatch dependency to avoid vulnerabilities

Jinpeng Miao • Feb 19, 2026

fe05293

Update ajv dependency to avoid vulnerabilities

Jinpeng Miao • Feb 18, 2026

9d2ca47

Quality

beta
Quality
high
Maturity
beta

Categories

Evals & BenchmarkingPrimaryDev Tools & AutomationLearning ResourcesSecurity & SafetyData Science & AnalyticsAI AgentsOther AI / MLFoundation Models

PM Skills

Safety & AlignmentData & EvaluationAI-Native Architecture

Languages

Python100.0%

Timeline

Project created
Dec 6, 2023
Forked
Mar 21, 2026
Your last push
4 months ago
Upstream last push
2 months ago
Tracked since
Mar 18, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…