Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
prompt-guard
prompt-guard is an open-source security skill for Claude Code and compatible agents, published by Orchestra-Research. Its author describes it as: “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 process…”. The project has 12k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add Orchestra-Research/AI-Research-SKILLs`.
What prompt-guard does
Prompt Guard is an 86M parameter classifier that detects prompt injections and jailbreak attempts in LLM applications.
Installation
Add prompt-guard to your agent with:
/plugin marketplace add Orchestra-Research/AI-Research-SKILLsAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for prompt-guard is organised into these sections:
- Quick start
- Common workflows
- Workflow 1: User input filtering (jailbreak detection)
- Workflow 2: Third-party data filtering (injection detection)
- Workflow 3: Batch processing for RAG
- When to use vs alternatives
- Common issues
- Threshold recommendations
- Hardware requirements
- Resources
When to use it
Reach for prompt-guard when you want security help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear MIT license — safe to read and adapt
- Ships in Orchestra-Research/AI-Research-SKILLs, an established project with 11,807 GitHub stars
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does prompt-guard do?
- 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.
- How do I install prompt-guard?
- Run /plugin marketplace add Orchestra-Research/AI-Research-SKILLs in your agent, then reload your skills. Review the source at https://github.com/Orchestra-Research/AI-Research-SKILLs before installing.
- Is prompt-guard free to use?
- Yes. prompt-guard is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Where does prompt-guard come from?
- prompt-guard ships inside Orchestra-Research/AI-Research-SKILLs, a repository that contains 41 catalogued skills in total. The repository's 11,807 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Security →
Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produces a structured review report with prioritized, actionable feedback. Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues. Invoke for PR reviews, code quality checks, refactoring suggestions, review code, code quality. Complements specialized skills (security-reviewer, test-master) by providing broad-scope review across correctness, performance, maintainability, and test coverage in a single pass.
A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.