Pricing

$0.05 / completed trust audit

Try for free

Go to Apify Store

AI Agent Security Scanner — Prompt Injection & Secrets

Try for free

Scan AI agent prompts, skill files and manifests for prompt injection, secret patterns, risky permissions and dependency signals. Get an explainable JSON report with redacted evidence. Rule-based checks; no input execution or external AI model.

Pricing

$0.05 / completed trust audit

Rating

0.0

(0)

Developer

azz backwardz

Actor stats

Bookmarked

Total users

Monthly active users

5 days ago

Last modified

Configure MCP server with AI Agent Security: Prompt Injection & Secret Scanner

The configuration above connects to the hosted Apify MCP server with the AI Agent Security: Prompt Injection & Secret Scanner Actor already loaded. It uses OAuth, so your client opens a browser window to sign you in to Apify on first use. No API token is needed. Clients without OAuth support can authenticate with an Authorization: Bearer header carrying an API token from API & Integrations in Apify Console.

Get a ready-to-use configuration for your MCP client with the AI Agent Security: Prompt Injection & Secret Scanner Actor preconfigured at https://mcp.apify.com/?tools=fetch-actor-details,azzbackwardz/agent-trust-auditor.

You can connect to the Apify MCP Server using clients like Tester MCP Client, or any other MCP client of your choice.

If you want to learn more about our Apify MCP implementation, check out our MCP documentation. To learn more about the Model Context Protocol in general, refer to the official MCP documentation or read our blog post.

Prompt Injection Dataset Scanner v2

zentrafoundry/prompt-injection-dataset-scanner-v2

Scan buyer-provided JSON rows or an existing Apify dataset for six explainable prompt-injection heuristics, then return per-row severity, matched signals, redacted evidence snippets, and a review action.

Zentra

🛡️ 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

Prompt Injection Web Scanner

q_services/prompt-injection-web-scanner

Scan webpages or text for prompt injection, secret exfiltration, hidden instructions and Unicode control characters.

Q Services

Prompt Injection Surface Scanner

civicdataworks/prompt-injection-surface-scanner

Scan public pages for prompt-injection phrases before they are indexed into RAG or used by agents.

Rowan Mercer

Prompt Injection Firewall MCP

reverberant_equality/mcp-prompt-injection-firewall

Heuristically scan untrusted text and public web pages for prompt-injection patterns, flag suspicious instructions, and separate them from retained content for safer AI-agent workflows.

Jordan C

Agent Security Scanner

folkloric_morale/agent-security-scanner

Scan AI agent repos, MCP servers, and coding-agent configs for unsafe eval, shell execution, package hallucinations, prompt injection, and MCP security risks.

ProofLayer

Agent Skill Security Scanner

scraper_guru/agent-skill-security-scanner

Scan Claude, Codex, Cursor, and skills.sh agent skills for prompt injection, secret access, unsafe commands, exfiltration, and supply-chain risks.

LIAICHI MUSTAPHA

Injection Shield - Prompt-Injection & Jailbreak Detector

apricot_blackberry/agent-injection-shield

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.