Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

prompt-protection

by mughalhereversion 4.4.0i★ 3iRuns on your computerOfficial site ↗
Registry nameio.github.mughalhere/prompt-protection

How to install

What it does

Scan prompts, tool definitions and model output for injection, and guard agent tool calls.

  • Connects Runs on your computer
  • Account or key No key needed
  • Category Search & AI memory

Use together with

Skills that teach the AI this kind of work; they work alongside this one

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

by google-research★ 35,6291 skills

Skill · How-to guide

Shadowbroker

Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…

by BigBodyCobain★ 11,6021 skills

Skill · How-to guide

google-maps-scraper

scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place

by gosom★ 8,2091 skills

Skill · How-to guide

Why it ranks here

Lists are ordered by a usage score (out of 100) built from these parts

Popularity27/80GitHub stars or weekly downloads: the larger counts 60, the smaller 20
Freshness12/12Full marks for a release or code change within 30 days
Still answering0/8The cloud endpoint answered at the last check
Usage score39/100

Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)

Install

Pick the AI app you use, then copy the settings.

Let your AI install it with one sentence

Please install prompt-protection. Follow https://mcp.popnx.com/i/mughalhere-prompt-protection.md, show me the commands and wait for my OK before running them.

Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads

Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 13, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude, with some setup first

Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

Let AI install it

Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server prompt-protection for Claude on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "prompt-protection": { "command": "npx", "args": [ "-y", "prompt-protection" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the prompt-protection tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Open the Claude desktop app’s settings file

    SettingsDeveloperEdit Config

  3. Paste these settings and save the file

    {
      "mcpServers": {
        "prompt-protection": {
          "command": "npx",
          "args": [
            "-y",
            "prompt-protection"
          ]
        }
      }
    }
  4. Quit Claude and open it again

  5. Try it

    Use prompt-protection and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using prompt-protection or shows a prompt-protection tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect prompt-protection yet

prompt-protection runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect prompt-protection

  • Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
  • Install Node.js on your computer first (one time)
  • Install Node.js on your computer first (one time)
  • Install Node.js on your computer first (one time)

B · Others in Search & AI memory that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code, with some setup first

Install Node.js on your computer first (one time)

Let AI install it

Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server prompt-protection for Claude Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user prompt-protection -- npx -y prompt-protection 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the prompt-protection tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  3. Paste this command and press Enter

    claude mcp add --scope user prompt-protection -- npx -y prompt-protection
  4. Type /mcp in Claude Code

    You should see prompt-protection listed as connected

  5. Try it

    Use prompt-protection and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using prompt-protection or shows a prompt-protection tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

Install Node.js on your computer first (one time)

Let AI install it

Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server prompt-protection for Cursor on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "prompt-protection": { "command": "npx", "args": [ "-y", "prompt-protection" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the prompt-protection tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  3. Open the AI chat in Cursor in Agent mode

  4. Try it

    Use prompt-protection and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using prompt-protection or shows a prompt-protection tool in the answer, you are connected

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

Install Node.js on your computer first (one time)

Let AI install it

Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server prompt-protection for VS Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "prompt-protection": { "type": "stdio", "command": "npx", "args": [ "-y", "prompt-protection" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the prompt-protection tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  3. Open the AI chat in VS Code in Agent mode

  4. Try it

    Use prompt-protection and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using prompt-protection or shows a prompt-protection tool in the answer, you are connected

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use prompt-protection💬 Discussion →
For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add --scope user prompt-protection -- npx -y prompt-protection

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "prompt-protection": {
      "command": "npx",
      "args": [
        "-y",
        "prompt-protection"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "prompt-protection": {
      "command": "npx",
      "args": [
        "-y",
        "prompt-protection"
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "prompt-protection": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "prompt-protection"
      ]
    }
  }
}

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
1,384/wk
Connection
Runs on your computer
Latest versioni
4.4.0
Published to registryi
Nov 5, 2026
Code last changedi
Nov 13, 2026
Maker
mughalhere
Packages
npm: prompt-protection
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account mughalhere, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 6 days ago

  • ✓ Pass

    Has a licence

    Uses MIT

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Published vulnerabilities (OSV.dev)

No entries on OSV.dev for prompt-protection@4.4.0

Checks only this package version, not every dependency · checked Nov 15, 2026

What we check → · JSON

Makers: ask for a re-check or report wrong info
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/mughalhere-prompt-protection.svg)](https://mcp.popnx.com/en/servers/mughalhere-prompt-protection)

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

User reviews

No reviews yet

Sign in to write a review

Compared with others in Search & AI memoryi

  • More stars than 86% of the other 6394 servers in this category
  • Published to the registry more recently than 75% of the other 6394 servers in this category
  • Basic checks equal to or better than 99% of the other 6394 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is prompt-protection safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 6 days ago, and the latest version (4.4.0) reached the registry 14 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)

Similar alternatives

Same category, other makers, commands already checked. Official ones first, then by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

OpenSEO

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

by every-appWidely used★ 28.2KUpdated 5 days ago

Runs in the cloud✓ everyapp.com

Exa

Connect AI agents to Exa for web search, content fetching, and multi-step research.

by exa-labsWidely used★ 5.2KUpdated 2 months ago

Runs in the cloud✓ service owner · exa.aiTried by the PopNx team

Microsoft Learn MCP

Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.

by MicrosoftDocsWidely used★ 2KUpdated 12 months ago

Runs in the cloud✓ service owner · microsoft.comTried by the PopNx team

Docs

Search and read Empryo's documentation. Read-only, no auth, no local access.

by proxysoulGrowing★ 1.6KUpdated 2 months ago

Runs in the cloud✓ empryo.com
Compared with similar ones
This one
prompt-protection
OpenSEOExaMicrosoft Learn MCPDocsCOTAL actions (cotal.ai)
Runs whereInstalls on your computerRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to install
Needs a keyNoNoNoNoNoNo
Add with + in ClaudeNoYesYesYesNoNo
Basic checks3/35/52/44/44/44/4
LicenseMITMITMITCC-BY-4.0NOASSERTIONApache-2.0
PriceNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registry

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

prompt-protection

A provenance-tracked tool-call guard for JavaScript agents. Tool results are tainted, destinations the user named are trusted, and every tool call the model proposes is checked before it runs: untrusted data does not reach a network, email, exec, file or payment sink. Fail-closed, in-process, zero runtime dependencies. Text detection, spotlighting and canaries ship as components, with their benchmark numbers published whether they flatter the library or not.

Listed in the Agent Threat Rules ADOPTERS registry (Tier 2, adapter), the official MCP registry as io.github.mughalhere/prompt-protection, MCPrush, and the XERJ Corpus Hub.

[Live Demo →](https://mughalhere.github.io/prompt-protection/)

What it is, and what it isn't

Prompt injection stopped being a text-classification problem the moment models started calling tools. The damage in an agent is a consequence, not a sentence: a URL lifted from an email ends up in an outbound request, an attendee address from a calendar entry becomes the recipient of send_email, a payload in a README lands in exec. Version 3 tracks where data came from and refuses to let untrusted data reach a dangerous sink. That is the capability model from Google DeepMind's CaMeL paper (arXiv 2503.18813), ported to a JavaScript tool-calling loop without the custom interpreter.

It is a policy layer inside your process. It is not an isolation boundary. It cannot see a flow that passes through the model's hidden state, a paraphrase that shares no identifiers with its source, or a source you never registered. The Limitations section lists what it misses, with the dataset rows that show it.

60-second agent quickstart

import { generateText } from 'ai';

import { createGuard } from 'prompt-protection/guard';

const guard = createGuard({ sinks: { http_post: 'network', send_email: 'email', run_shell: 'exec' }, // or rely on name heuristics });

guard.analyzeUserTurn(userMessage); // destinations the user names become trusted

const result = await generateText({ model, tools: guard.wrapTools(tools), // check → execute → taint result toolApproval: guard.vercelToolApproval(), // block → denied, confirm → user-approval prompt: userMessage, });

Or drive it by hand:

guard.taint('read_email', emailBody);         // label a tool result as untrusted

const decision = guard.checkToolCall({ toolName: 'http_post', args: { url } }); // { action: 'block', policy: 'untrusted-to-exfil-sink', reasons: ['untrusted-to-exfil-sink'], flows: [{ kind: 'identifier', path: 'args.url', … }] }

Taint survives three places it used to leak (4.1):

// Memory: persist the entry next to the value, read it back next session with its lineage.

const { store, entry } = guard.taintMemoryWrite('summarise', summary, { key: 'notes/today' }); if (store) await db.put(entry.key, { value: summary, entry }); // … later, in a new guard: guard.memoryRead([savedEntry]); // a blocked lineage into an exfil/exec sink → 'lineage-untrusted'

// Sub-agents: the child guard inherits sources, labels and trusted identifiers; depth increments. const child = guard.fork(); // or createGuard({ inherit: guard.handoff() }) across a boundary

// Approvals: what the human saw is what runs. const card = await guard.approvalCard(call); // rendered fields, tainted marks, card.digest guard.confirm(card.id, card.digest, 'alice'); // UI echoes the digest back guard.checkToolCall(call); // identical args → allow ('approved'); changed args → block ('approval-mismatch')

Every decision carries reasons: DecisionReason[] (stable codes, docs/CONFORMANCE.md) and depth.

Static structure (4.2): pin what the agent may call, and bound how often.

const lock = await guard.pin(tools);          // digests name, description, schema, annotations; persist it

// … next process: guard.lock(savedLock); await guard.verify(tools) guard.wrapTools(tools); // a redefined description now blocks with 'tool-drift' guard.checkToolCall({ toolName: 'new_tool', args }); // unlisted under a lock → 'tool-unpinned'

createGuard({ budgets: { maxCallsPerTurn: 20, maxRepeatIdentical: 3, maxDepth: 2 } }); // the 4th identical call, or the 21st this turn → 'budget-exceeded'

import { createBoundary } from 'prompt-protection/spotlight'; const boundary = createBoundary({ mode: 'datamark' }); createGuard({ spotlight: boundary }); // one marker, one system-prompt sentence: boundary.instruction

Under a lock, readOnlyHint: true makes a tool a non-sink and an unannotated tool the name heuristics cannot place resolves to unknown (treated as exfil and exec) unless you set annotationsDefault: 'heuristic' or name its sink in sinks.

Operability (4.3): pick a preset, observe before you enforce, and read the reason chain.

createGuard({ preset: 'strict' });            // 'balanced' (default) · 'strict' · 'permissive'; explicit options win

createGuard({ mode: 'observe' }); // action is always 'allow'; decision.observedAction is the verdict import { explain } from 'prompt-protection/guard'; explain(decision); // { summary, chain: [{ code, policy, because, flows }] }

One call per framework:

import { protect } from 'prompt-protection/adapters/vercel-guardrail';   // ai ≥ 6

const { tools, toolApproval, prepareStep, onToolExecutionEnd, stopWhen } = protect(guard, myTools); new WorkflowAgent({ tools, toolApproval, prepareStep, onToolExecutionEnd, stopWhen }); // WorkflowAgent has no default step limit

import { protect } from 'prompt-protection/adapters/openai-agents'; // @openai/agents ≥ 0.18 const { inputGuardrails, wrapTool } = protect(guard); new Agent({ inputGuardrails, tools: [wrapTool(sendEmail)] }); // tool guardrails + needsApproval bound per tool

import { protect, interruptWhen } from 'prompt-protection/adapters/langchain'; // langchain ≥ 1 createAgent({ middleware: [await protect(guard), humanInTheLoopMiddleware({ interruptOn: { stripe_transfer: { allowedDecisions: ['approve', 'reject'], when: interruptWhen(guard) } } })] });

Output side: analyzeOutput(text, { renderAllowlist: ['ourcompany.com', '*.cdn.ourcompany.com'], conversation }) blocks markdown/HTML that would render or link an unlisted host, a data: URI, or a query parameter carrying high-entropy or conversation-derived data (off unless the allowlist is set). redact(text) and analyzeOutput(text, { redact: 'all' }) replace secrets and PII (gitleaks / Presidio shapes, checksums validated in code).

Trust across boundaries (4.4, preview): a label is only worth what signs it.

import { seal, generateKey } from 'prompt-protection/envelope';

const key = await generateKey('HS256', 'k1'); // or 'EdDSA' (Ed25519, Node ≥ 20.19.3) const env = await seal(toolResult, key, { label: 'tool', ttlMs: 60_000, from: 'fetcher' }); // … in the receiving process: const { opened, error } = await guard.taintEnvelope(env, key); // forged / expired / replayed → a blocked source const child = await guard.sealHandoff(key); // sealed TaintHandoff for a sub-agent elsewhere await other.absorbSealed(child, key); // bad seal → 'handoff-untrusted' on any flow const entry = await guard.sealMemoryEntry(write.entry); // memoryReadSealed() reads unsigned entries as blocked

Architecture

tool result ──taint──▶ provenance label ──▶ shingles + identifiers (URL, host, email, path, token)

│ model proposes tool call ──▶ sink class ──▶ flow detection (exact / identifier / content) ──▶ policies ──▶ allow · flag · confirm · block ▲ ▲ explicit map or name heuristics plan() allow-list · user-trusted destinations

The default policies run in this order. plan-violation blocks any tool outside the plan() allow-list. injection-source-flow blocks when a source that itself scored as injection flows anywhere. untrusted-to-exfil-sink blocks untrusted data reaching network, email or messaging tools, and untrusted-to-exec does the same for exec and file writes. untrusted-to-payment asks for confirmation. injection-then-sink flags a sink call made in the same turn as an injection-scored source even when no flow was detected, because paraphrase is exactly the case the flow detectors miss. args-injection flags when the arguments themselves read as injection. Each of these is one of the patterns in *Design Patterns for Securing LLM Agents* (arXiv 2506.08837): Action-Selector via plan(), Plan-Then-Execute, Context-Minimisation via spotlighting.

Spotlighting (prompt-protection/spotlight, arXiv 2403.14720) marks untrusted spans by delimiting, datamarking or base64-encoding them, and gives you the system-prompt sentence that tells the model what the marker means. With wrapTools({ spotlight: 'datamark' }) the model sees marked text while the guard taints the original, and arguments are unmarked before flow detection so a copied span still matches.

Canaries (prompt-protection/canary) put a token in the system prompt and look for it in the output in exact, normalized, spaced, base64, hex, reversed and partial forms. There is also a shingle-similarity check between the output and the system prompt. Plain verbatim canaries were shown to fail against paraphrase (arXiv 2506.19109). Similarity closes part of that gap. Not all of it.

Text detection is a component, not the product: 106 input rules, 21 output rules and 9 tool-poisoning rules score text that has to be scored, and the Benchmark section says how well. An embedded 33 KB int8 n-gram classifier lives on prompt-protection/ml (preview tier, off by default, for reasons the benchmark explains). prompt-protection/lite is the rules-only entry at 20 KB gzipped.

Benchmark

npm run bench runs the shipped build against every set below and writes bench/results.json. The same run is a CI gate. Recall and false-positive rate are shown as regex / ml / hybrid; the shipped default is regex.

SetLicenceN (attack/benign)RecallFalse-positive rate
NotInject, over-defence benchmark (arXiv 2410.22770)MIT339 (0/339)n/a2.9% / 7.7% / 10.6%

| datasets/benign-hard + datasets/attacks, ours, written to evade proximity matching | CC-BY-4.0 | 285 (130/155) | 14.6% / 19.2% / 30.8

Only the beginning is shown; read the rest in the repo