DKnownAI Guard is a security API for AI agents that detects prompt injection, jailbreak, and agent hijacking attempts and classifies each request into four risk levels.
About
DKnownAI Guard is a security API designed specifically for agentic AI systems — applications where a large language model can execute code, read and write files, call tools, or touch production systems. Its core job is to detect when a user is attempting to manipulate the agent through prompt injection, jailbreaks, system prompt extraction, or role-play escapes, and to stop those attempts before the agent acts on them.
The product differs from conventional content moderation, which asks whether text is inherently harmful. DKnownAI Guard instead evaluates intent: whether someone is trying to deceive the agent into misbehaving. Each request is returned with one of four labels — AGENT_HACK, SYS_FLAG, CONTENT_FLAG, or SAFE — along with a recommended action. This lets teams block hijacking attempts outright while leaving routine, legitimate operations (even risky ones like database changes) under developer control. The vendor, DKnownAI, offers a REST API, documentation, a blog, and an interactive playground on its site.
Key Features
Pricing & Fees
- Pricing: A Free plan costs $0 per month with 1,000 API calls, all four classifications, multilingual support, the REST API, and email support. A Pro plan costs $1.99 per month (first month $0.99) with 5,000 API calls, all Free features, and priority technical support; a higher tier is listed as coming soon.
- Free tier available: The free plan requires no payment and includes full access to all four classification signals.
- Distinguishes operational from content risk: The same destructive command is treated differently depending on whether it arrives via deception (blocked) or a direct request (developer decides), preserving agent autonomy.
Who It's For
DKnownAI Guard targets developers and engineering teams building AI agents that perform real actions — running code, modifying databases, managing server configurations, or calling external tools. Typical users include platform engineers hardening agentic workflows, security-minded SaaS teams adding guardrails to customer-facing agents, and builders working with frameworks like Claude Code, Manus, or OpenClaw. It suits organizations that want to block manipulation attempts automatically while retaining human or policy control over risky but legitimate system operations, as well as teams that must monitor content for compliance red lines.
FAQ
What is DKnownAI Guard?DKnownAI Guard is a security API for AI agents that detects prompt injection, jailbreak, and hijacking attempts and classifies every request into one of four risk levels: AGENT_HACK, SYS_FLAG, CONTENT_FLAG, or SAFE.
Is there a free plan?Yes. The Free plan costs $0 per month and includes 1,000 API calls, all four classifications, multilingual support, the REST API, and email support; a Pro plan at $1.99 per month raises the limit to 5,000 calls.
Which platforms and agent frameworks does it support?It is a language-agnostic REST API designed for agentic systems, and the vendor specifically names Claude Code, Manus, and OpenClaw as target environments.
How is it different from traditional content moderation?Content moderation flags harmful text, whereas DKnownAI Guard focuses on whether someone is trying to manipulate the agent, so legitimate but risky operations from authorized users are not automatically blocked.
Does it work in languages other than English?Yes, the API supports more than 100 languages and can optionally use conversation context to improve classification accuracy.
Related Tutorials
View all →
Related Tools
View all →
Exa Exa is a web search API and research platform that gives AI agents real-time access to web pages, structured company and people data, and deep research results. 
Composio Composio is an integration platform that gives AI agents and LLMs secure access to 1,500+ apps, with managed authentication, tool execution, skills, and enterprise governance controls. 
OpenRouter OpenRouter is a unified, OpenAI-compatible API that gives developers pay-as-you-go access to 500+ AI models for text, image, video, and audio from 80+ providers. 
OmniRoute - Free AI Gateway for Multi-Provider LLMs Free, open-source AI router with auto-fallback. 236 providers, one endpoint, 95 MCP tools, 17 routing strategies, A2A protocol, auto-combo engine, semantic cache, memory & skills. Deploy anywhere. 
LangChain LangChain provides a comprehensive suite of products to support developers throughout their entire development workflow.