Lasso Security: runtime security layer for LLM apps and agents
Lasso Security is a runtime security layer for LLM apps and agents from Lasso Security. It is a commercial product offered as: API, Self-hosted. Pricing model: not published.
Teams that already route LLM traffic through an AI gateway and want to add inline detection and blocking without code changes
Buyers who want runtime guardrails, agent discovery and red teaming from one vendor and can work through a sales-led evaluation
Consider instead if
You want a standalone hosted guardrail API that your own application calls.
See Lakera Guard.
You want an open-source library you can modify and run entirely yourself.
See NeMo Guardrails.
What Lasso Security does
Lasso Security sells a wide AI security platform; this listing covers its runtime guardrail, which enforces policy inline at a proxy, API or AI gateway. A use-case page says it plugs into Kong, Envoy AI Gateway, TrueFoundry, Portkey or LiteLLM without code changes. It flags direct and indirect prompt injection and inputs meant to push an agent into unauthorized actions, can block, mask or alert on sensitive data, and keeps audit trails of agent decisions. A September 2026 release adds CPU-based guardrails that run where customer data must stay. The same site sells discovery, posture management and automated red teaming modules, and discovery connects to agent builders such as Amazon Bedrock and Vertex AI. The docs sit behind a login and prices are not published, so expect a sales-led evaluation.
This summary is our own wording of the sourced facts on this page.
Key facts
Each value links to the page that states it, with the date we checked it.
Where Lasso Security fits in our AI security layers
Our analysis
Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document.
How the model works.
AI security layers that Lasso Security covers, with the role, how each applies and what it rests on
Data loss prevention policies can block or mask sensitive data.
Blocks, masks or alerts on sensitive data under data loss prevention policies
Not mapped in our analysis: LLM05, LLM07, LLM09, LLM10.
These are risks we expect tools in this category to cover; the sources we checked do not document a matching capability.
Routes LLM traffic through Kong with prompt guards, PII sanitization, spend limits and observability.
Best for: Teams that already run Kong as an API gateway and want LLM routing and prompt controls on the same data plane
65Coverage Score 65 out of 100
LLM01 Prompt Injection
LLM02 Sensitive Information Disclosure
LLM10 Unbounded Consumption
Reviewed
Lasso Security FAQ
Is Lasso Security open source?
No. The platform is commercial. The vendor's GitHub organization has public repositories such as an MCP gateway under the MIT license, but none is the platform itself.
Which AI gateways does Lasso Security work with?
Its AI Gateway Security page lists Kong, Envoy AI Gateway, TrueFoundry, Portkey and LiteLLM, and says the integration needs no source code changes.
Does Lasso Security publish prices?
No. The homepage lists no pricing and offers a demo and a free assessment.
Does Lasso Security cover more than guardrails?
Yes. The site navigation lists discovery with an AI bill of materials, AI security posture management, automated red teaming and AI detection and response next to runtime enforcement. Discovery connects to agent builders such as Amazon Bedrock and Google Vertex AI. This listing covers the runtime guardrail.
We have no commercial relationship with Lasso Security.
Sources & last reviewed
Last reviewed . We compile from the vendors' own public
pages and repositories and we do not run the products. Source links open in a new tab. Found a mistake? Report a correction.
We may use analytics and, later, show ads. They stay off until you choose, wherever you are. Declining
never limits what you can read. See our privacy policy and
cookie policy.
Privacy settings
Choose what you allow. Your choice is stored on this device for 13 months. You can change it later from the
"Privacy choices" link in the footer.