Under maintenance

Pricing

Pay per event

Try for free

Go to Apify Store

Injection Shield - Prompt-Injection & Jailbreak Detector

Under maintenance

Try for free

Stop prompt-injection and jailbreaks before your agent reads them. Scans tool results, web pages, and user input for instruction-override, hidden Unicode tag-smuggling, ChatML token injection, and 30+ attack patterns. Returns a risk score, flags, and sanitized text.

Pricing

Pay per event

Rating

0.0

(0)

Developer

Creator Fusion

Actor stats

Bookmarked

Total users

Monthly active users

2 days ago

Last modified

Prompt-Injection & Jailbreak Detector for AI Agents API through CLI

The Apify CLI is the official tool that allows you to use Injection Shield - Prompt-Injection & Jailbreak Detector locally, providing convenience functions and automatic retries on errors.

Install Apify CLI

Using installation script (macOS/Linux):

$curl -fsSL https://apify.com/install-cli.sh | bash

Using installation script (Windows):

$irm https://apify.com/install-cli.ps1 | iex

Using Homebrew:

$brew install apify-cli

Using npm:

$npm install -g apify-cli

Other API clients include:

Injection Shield - Prompt-Injection & Jailbreak Detector API in Python

Injection Shield - Prompt-Injection & Jailbreak Detector API in JavaScript

Injection Shield - Prompt-Injection & Jailbreak Detector OpenAPI definition

Injection Shield - Prompt-Injection & Jailbreak Detector API

M2MCent: 1,000+ Agentic Services

evozim/m2mcent-1000-agentic-services

The ultimate API gateway for AI Agents. Access 1,004+ real-world microservices (from crypto to logistics) through a single Actor. Features built-in x402 programmatic crypto settlement on Base Mainnet and MCP protocol integration. Send toolName="list" to view all available tools.

Hector Ventura

AI Agent Effect Firewall

tmas_from_iceland/ai-agent-effect-firewall

Execution firewall for AI agents. Blocks untrusted inputs from triggering real-world actions by enforcing decision-level allow / deny / approval gates. Infrastructure safety layer for tool-enabled agents

Tomasz Trojanowski

Prompt Injection & Jailbreak Payload Corpus

jungle_synthesizer/prompt-injection-jailbreak-payload-corpus-scraper

Normalizes published prompt-injection and jailbreak datasets from HuggingFace and GitHub research repos into one labeled corpus: technique, target model, defense bypassed, license, cross-source dedup. Defensive only — aggregates public data for guardrail/eval testing, never targets a live LLM.

BowTiedRaccoon

🛡️ AI Agent & MCP Security Scanner

inexhaustible_glass/agent-security-scanner

Scan GitHub repos for AI-agent, MCP-server & skill security risks: prompt injection, tool poisoning, hallucinated packages, secrets & dangerous code.

Hitman studio

Restaurant Menu Scraper: Pay Only for Successful Results

salesmap-ai/url-to-menu-restaurant-menu-scraper

Extract structured menu data: dishes, prices, sections, dietary tags from any restaurant URL, including scanned PDFs and photo menus. Per-URL status codes show exactly what succeeded; you're never charged for failures.

Salesmap Lee

All-in-One Instagram Scraper

get-leads/all-in-one-instagram-scraper

Instagram scraper — 11 modes: profiles, posts, reels, comments, hashtags, tagged, search, followers count & more. No browser needed — HTTP-only, 256MB, fast. Premium residential proxy (~95% success rate). Pay per result: 40% cheaper. MCP-ready for AI agents.

Japi Cricket

313

5.0

(1)

AI Context Scraper

wheat_tourist/ai-context-scraper

AI Context Scraper is a production-grade Apify Actor that gathers high-quality coding context from the Web, GitHub, and StackOverflow for AI agents and RAG systems. It uses NVIDIA Nemotron 3 Super to synthesize documents, code snippets, and patterns into actionable implementation guidance.

Varun Chopra

Agent Trust Auditor

azzbackwardz/agent-trust-auditor

Deterministic security and trust auditing for AI agent prompts, skill files, manifests, and configuration text. Detects prompt injection, exposed credential patterns, risky permissions, dependency risks, and licensing signals without executing submitted content.

azz backwardz

Repo Security Scanner — Malicious Code & Supply Chain

eltociear/mcp-server-security-scanner

Run a supply chain audit on any GitHub repo before you install or depend on it. Scans for malicious code, install-time execution, credential exfiltration and prompt injection. Vet npm/PyPI package sources and MCP servers. Risk level, score and file/line evidence per repo.