Back to skills
SkillHub ClubWrite Technical DocsFull StackDevOpsData / AI

prompt-guard

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Packaged view

This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.

Stars
5,196
Hot score
99
Updated
March 20, 2026
Overall rating
C4.0
Composite score
4.0
Best-practice grade
B81.2

Install command

npx @skill-hub/cli install orchestra-research-ai-research-skills-prompt-guard
Safety AlignmentPrompt InjectionJailbreak DetectionMetaInput ValidationSecurityContent FilteringMultilingual

Repository

Orchestra-Research/AI-Research-SKILLs

Skill path: 07-safety-alignment/prompt-guard

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Open repository

Best for

Primary workflow: Write Technical Docs.

Technical facets: Full Stack, DevOps, Data / AI, Tech Writer, Security.

Target audience: Development teams looking for install-ready agent workflows..

License: Unknown.

Original source

Catalog source: SkillHub Club.

Repository owner: Orchestra-Research.

This is still a mirrored public skill entry. Review the repository before installing into production workflows.

What it helps with

  • Install prompt-guard into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
  • Review https://github.com/Orchestra-Research/AI-Research-SKILLs before adding prompt-guard to shared team environments
  • Use prompt-guard for development workflows

Works across

Claude CodeCodex CLIGemini CLIOpenCode

Favorites: 0.

Sub-skills: 0.

Aggregator: No.