AI Defense Stack

LLM firewalls & guardrails

Vigil: experimental prompt injection scanner

Vigil is an experimental prompt injection scanner from deadbits. It is open source under the Apache-2.0 license and is offered as: Library, Self-hosted, API.

  • Last reviewed
Visit Vigil (opens in a new tab) Documentation (opens in a new tab) Source code (opens in a new tab)
Open sourceApache-2.0 Layer 6: Runtime guardrails

Best for

Researchers and builders who want a modular, self-hosted prompt injection scanner with editable YARA rules

Consider instead if

  • You want an open-source guardrails library with more recent development activity. See NeMo Guardrails.
  • You prefer a hosted API over installing and tuning a scanner yourself. See Lakera Guard.

What Vigil does

Vigil is an open-source Python library and REST API that scans LLM prompts and responses for prompt injections, jailbreaks and other risky inputs. Its README lists several detection methods: vector database similarity, YARA heuristics with custom signatures, a transformer model, prompt-response similarity and canary tokens for prompt leakage and goal hijacking. Scanners are modular. You install it from source, configure a server file, and either run the REST server or import the Vigil class in your application. It is Apache-2.0 licensed and free. The README says it is in an alpha state, experimental and for research purposes, and should not be your only defense.

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.

Vendor
deadbits Source, checked October 21, 2026: github.com (opens in a new tab)
Status
Active Source, checked October 21, 2026: api.github.com (opens in a new tab)
Open source
Yes: Apache-2.0 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Repository
github.com Source, checked October 21, 2026: api.github.com (opens in a new tab)
GitHub stars
507 as of October 21, 2026 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Latest push
January 31, 2024 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Latest release
Not documented in the sources we checked
Deployment
Library, Self-hosted, API Source, checked October 21, 2026: github.com (opens in a new tab)
Pricing model
Free Source, checked October 21, 2026: github.com (opens in a new tab)
Website
github.com Source, checked October 21, 2026: github.com (opens in a new tab)
Documentation
github.com Source, checked October 21, 2026: github.com (opens in a new tab)
API reference
Not documented in the sources we checked
Quickstart
Not documented in the sources we checked
Security page
Not documented in the sources we checked
Attestations or disclosure
Not documented in the sources we checked

Capabilities

As documented by the vendor or project. The tag is our label from a controlled vocabulary.

Where Vigil 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 Vigil covers, with the role, how each applies and what it rests on
LayerRoleHow it appliesBased on
L6 Runtime Runtime guardrails Primary Screen what goes into and comes out of a model in live traffic, and limit abuse of the model endpoint. Follows its category, LLM firewalls & guardrails

OWASP LLM Top 10 mapping

Our analysis

The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.

OWASP LLM risks mapped to Vigil, with the capabilities each mapping rests on
RiskHow it appliesBased on
LLM01 Prompt Injection Detects prompt injections and jailbreaks with similarity search, YARA rules and a classifier. Scans prompts for injection by comparing them with known attacks in a vector database and with a transformer model; Describes itself as a detector for jailbreaks and other risky LLM inputs
LLM07 System Prompt Leakage Canary tokens flag prompt leakage. Uses canary tokens to detect prompt leakage and goal hijacking

Not mapped in our analysis: LLM02, LLM05, LLM09, LLM10. These are risks we expect tools in this category to cover; the sources we checked do not document a matching capability.

Alternatives and related tools

More in LLM firewalls & guardrails, ranked within the category by Coverage Score.

NVIDIA NeMo Guardrails

NVIDIA

Open sourceApache-2.0
  • Library
  • Self-hosted
  • API

Adds programmable input, dialog, retrieval, execution and output rails to LLM applications.

Best for: Teams that want to script rules for one LLM application in Python and run them in their own infrastructure

Coverage Score 76 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM05 Improper Output Handling
  • LLM06 Excessive Agency

Reviewed

Portkey AI Gateway

Palo Alto Networks (Portkey)

Open sourceMIT Freemium Now Prisma AIRS AI Gateway
  • SaaS
  • Self-hosted
  • API

Routes LLM traffic through one gateway API and runs input and output guardrail checks on each request.

Best for: Teams that want a single gateway for several LLM providers with guardrail checks, available as open source or as a hosted service

Coverage Score 69 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM05 Improper Output Handling
  • LLM09 Misinformation

Reviewed

Kong AI Gateway

Kong

Open sourceApache-2.0
  • Self-hosted
  • SaaS
  • API

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

Coverage Score 65 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM10 Unbounded Consumption

Reviewed

Vigil FAQ

Is Vigil open source?

Yes. It is released under the Apache-2.0 license, and the code is on GitHub at deadbits/vigil-llm.

Is Vigil production ready?

The README says Vigil is in an alpha state, experimental and for research purposes, and should not be your only defense.

How do I run Vigil?

Install it from the repository, configure the server file, then run the REST API server or import the Vigil class into your Python application.

Key facts you can cite

We have no commercial relationship with deadbits.

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.