nuguard

AI-SBOM generation, static analysis, and automated red-teaming / adversarial-attack-generation for AI agents and applications.

License: Apache 2.0 PR Tests PyPI Python versions GitHub Stars

What it does · See it in action · Framework coverage · Comparison · Getting started · FAQ

NuGuard is an open source AI application security toolkit. It generates an AI Bill of Materials (AI-SBOM) for your agentic application, statically analyzes it for structural risk, then red-teams a running instance with a catalog of 100+ adversarial scenarios — prompt injection, tool abuse, data exfiltration, and more — so you find the finding before an attacker does.

What It Does

AI SBOM: Agents, Tools, API End Points, Models. Analyze: static risk scan, OWASP/MITRE mapping. Policy: Application's Intended Behavior. Behavior: Functional tests, allowed topics. Red-team: 100+ adversarial scenarios, sandboxed. Data exfil findings. Remediate: fixes for specific application components. Export: text, JSON, Markdown, SARIF.

See It In Action

A real scan of a live fintech agent — Pinnacle Bank Assistant — walking through all five NuGuard stages: AI-SBOM, Cognitive Policy, Static Analysis, Behavior, and Red-Team. No mocks, no slides — real findings, including a live transcript of the agent leaking another customer's flagged fraud transactions on a routine question.

Animated walkthrough of the NuGuard pipeline against Pinnacle Bank Assistant: SBOM discovery (159 nodes), Cognitive Policy (19 controls, 4 enforcement gaps), Static Analysis (621 findings), Behavior testing (risk score 59.8/100), and Red-Team (risk score 40.3/100, 37 findings, including a cross-account data leak).

→ Open the interactive demo — scroll through the full walkthrough yourself.

Comparison

Capability comparison cards. NuGuard: AI-SBOM generation, supply-chain analysis, policy engine, adaptive multi-turn attacks, OWASP LLM Top 10 mapping, auto remediation — all six. Garak: adaptive multi-turn attacks only. Promptfoo: adaptive multi-turn attacks and OWASP LLM Top 10 mapping.

Getting Started

Install, then generate an SBOM, statically analyze it, and red-team a live target:

pip install nuguard

nuguard init --target <your-app-url>
nuguard sbom generate --source <path-to-your-app> --output app.sbom.json
nuguard analyze --sbom app.sbom.json --format markdown
nuguard redteam --config nuguard.yaml --format markdown --output reports/redteam.md

🚀 Ready to run NuGuard?

Installation, the full CLI surface, and the configuration reference — all in one guide.

Read the Quick Start guide

🤖 Using Claude Code?

Install the NuGuard plugin and run SBOM, analysis, behavior, and red-team scans directly from Claude Code or Claude Desktop.

Read the Plugin Guide

Hosted Version

NuGuard.ai NuGuard.ai

A managed SaaS version of NuGuard, with additional features and support on top of everything in this repo. Free trial available.

Supports RBAC, executive dashboards, audit-ready reports, policy checks, and integrations (ServiceNow AI Control Tower).

Visit NuGuard.ai

Contributing

🤝 Want to contribute?

Dev setup, running tests and lint, and the pull request process are covered in the Contributing guide.

Read the Contributing guide

Repo Notes

  • The repository currently contains example applications under tests/apps/
  • LLM-assisted features depend on provider credentials being available via environment variables

FAQ

I have some questions, how do I reach out to folks behind this repo? You can contact us at oss@nuguard.ai For bug reporting, use the issues page on GitHub.

Do I need a live app to get findings? No. nuguard sbom + nuguard analyze find structural and supply-chain risk statically. nuguard behavior and nuguard redteam need a running target typically in a sandbox.

Which LLM providers are supported for LLM-assisted features? Configured via the llm section of nuguard.yaml; provider credentials are read from environment variables. Lite LLM is used to abstract any llm provider.

What if I don't want to run all redteam scenarios? Filter by category or profile, or set enabled: false per scenario in a catalog exported with nuguard redteam catalog-export.

License

Apache 2.0.

Docs: Getting started · Quick start · CLI reference · Policy engine · Static analysis · Red-team Guide · Claude plugin · Troubleshooting · Security · Contributing

Project links

Data verified by PyPI on Sep 4, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for ranjangoel from gravatar.com ranjangoel

Credits

Author: NuGuard

GitHub Statistics

Data verified by PyPI on Sep 4, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

Apache Software License (Apache-2.0)

Requires

Python >=3.12

Provides Extra

browser dev mcp secrets spdx

Tags

agent ai appsec llm prompt-injection red-team sbom security

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nuguard-0.9.6.tar.gz (1.5 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nuguard-0.9.6-py3-none-any.whl (1.8 MB view details)

Uploaded Python 3

File details

Details for the file nuguard-0.9.6.tar.gz.

File metadata

  • Download URL: nuguard-0.9.6.tar.gz
  • Upload date:
  • Size: 1.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for nuguard-0.9.6.tar.gz
Algorithm Hash digest
SHA256 4b0ab5b507232308ac3e0a42a0b8bd26c436cc5f7d58c74cc94790c08080d8a1
MD5 93648dbf0b530181e3524a33c89c5723
BLAKE2b-256 abfb1cb0933d0191552fa22750361362f0ad4f04f1543dedf7e2051b49985f91

See more details on using hashes here.

Provenance

The following attestation bundles were made for nuguard-0.9.6.tar.gz:

Publisher: publish-pypi.yml on NuGuardAI/nuguard

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file nuguard-0.9.6-py3-none-any.whl.

File metadata

  • Download URL: nuguard-0.9.6-py3-none-any.whl
  • Upload date:
  • Size: 1.8 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for nuguard-0.9.6-py3-none-any.whl
Algorithm Hash digest
SHA256 20d1adcda9d319a552cfa20383db919cb95e9301d15baf8d675aa3788e9f52da
MD5 58426fcccde87f0128e3684b11b9608c
BLAKE2b-256 e485b4d972786df14dbda67c5fe83c0070aeb46571613bc9cdfd94cae719f17f

See more details on using hashes here.

Provenance

The following attestation bundles were made for nuguard-0.9.6-py3-none-any.whl:

Publisher: publish-pypi.yml on NuGuardAI/nuguard

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

0.9.6 This release

2 files

0.9.5

2 files

0.9.4

2 files

0.9.3

2 files

0.9.2

2 files

0.9.1

2 files

0.8.10

2 files

0.8.9

2 files

0.8.8

2 files

0.8.7

2 files

0.8.6

2 files

0.8.5

2 files

0.8.4

2 files

0.8.3

2 files

0.8.2

2 files

0.8.1

2 files

0.7.9

2 files

0.7.8

2 files

0.7.7

2 files

0.7.6

2 files

0.7.5

2 files

0.7.4

2 files

0.7.3

2 files

0.7.2

2 files

0.7.1

2 files

0.6.2

2 files

0.5.10

2 files

0.5.9

2 files

0.5.8

2 files

0.5.7

2 files

0.5.6

2 files

0.5.5

2 files

0.5.4

2 files

0.5.3

2 files

0.5.2

2 files

0.5.1

2 files

0.5.0

2 files

0.4.8

2 files

0.4.7

2 files

0.4.6

2 files

0.4.5

2 files

0.4.4

2 files

0.4.3

2 files

0.4.2

2 files

0.4.1

2 files

0.4.0

2 files

0.3.2

2 files

0.3.1

2 files

Yanked

0.3.0

2 files

Yanked reason: deprecated

0.2.0

2 files

Yanked

0.1.0

2 files

Yanked reason: too old

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page