prompt-guard

prompt-guard is a skill for Claude Code, Codex from OpenLAIR/dr-claw. It costs 65 tokens per session (2,433 once invoked), scanned B, original, no licence file.

A security filter that detects prompt injection and jailbreak attempts in prompts or data sent to language-model applications.

In plain words
What is it for?
Use it to screen prompts and third-party data before they reach an LLM, including content used in retrieval-augmented generation (RAG) systems.
Why use it?
It helps prevent malicious instructions in user input or retrieved content from changing an AI system's intended behavior.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to screen prompts and third-party data before they reach an LLM, including content used in retrieval-augmented generation (RAG) systems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openlair/dr-claw/prompt-guard
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add OpenLAIR/dr-claw --skill prompt-guard
Clone the repo
git clone --depth 1 https://github.com/OpenLAIR/dr-claw

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prompt-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/openlair/dr-claw/prompt-guard/github.svg)](https://agentmods.dev/skills/openlair/dr-claw/prompt-guard)
Your own site
<a href="https://agentmods.dev/skills/openlair/dr-claw/prompt-guard"><img src="https://agentmods.dev/badge/skills/openlair/dr-claw/prompt-guard/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prompt-guard

Your own site · 80×15
<a href="https://agentmods.dev/skills/openlair/dr-claw/prompt-guard"><img src="https://agentmods.dev/badge/skills/openlair/dr-claw/prompt-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,433 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.02433
Opus 5 $0.00032 $0.01216
Sonnet 5 $0.00013 $0.00487
Haiku 4.5 $0.00006 $0.00243

Measured 7d ago against content hash 0291e30b5549, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

prompt-guard scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

score = get_jailbreak_score("Ignore previous instructions")

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/safety-alignment/prompt-guard/SKILL.md · 313 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 313 lines · 65 tokens per session scan B 0291e30b5549

Subscribe to this mod's changes

prompt-guard is a skill published in the GitHub repository OpenLAIR/dr-claw (1,091 stars, last pushed today), with no licence file. It adds 65 tokens to every session and 2,433 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

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.

liortesta/ClawdAgent · 65 tokens

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.

Orchestra-Research/AI-Research-SKILLs · 65 tokens

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.

ihatesea69/HieuNghi-AI-Skills · 65 tokens

markitdown

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

K-Dense-AI/scientific-agent-skills · 61 tokens

llamaguard

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

davila7/claude-code-templates · 74 tokens

sentence-transformers

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production…

davila7/claude-code-templates · 67 tokens