Skip to main content

AgentGuard

AgentGuard is a GitHub Action that detects authorization and tenant-isolation regressions in Python/Django pull requests, especially AI-generated ones.

Install

pip install agentguard

Dev setup

# Clone the repo
cd agentguard

# Install with uv (recommended)
uv sync --dev

# Or with pip
pip install -e ".[dev]"

Test commands

# Run all tests
pytest

# Run with coverage
pytest --cov=src/agentguard

# Lint
ruff check src/ tests/

# Format
ruff format src/ tests/

# Type check
mypy --strict src/

CLI usage

agentguard version
agentguard scan --base main --head feature-branch --format json --mode observe --output report.json

GitHub Action

See .github/workflows/ci.yml for the CI pipeline and action.yml for the composite action.

Metadata

Release files for agentguard-sentry 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agentguard-sentry 0.1.0
File Size Uploaded Provenance Actions
agentguard_sentry-0.1.0.tar.gz 19.7 kB Without provenance Details for agentguard_sentry-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for agentguard-sentry 0.1.0
File Interpreter ABI Platform Actions
agentguard_sentry-0.1.0-py3-none-any.whl Python 3 none any Details for agentguard_sentry-0.1.0-py3-none-any.whl

Total release size: 21.5 kB

Release files / agentguard_sentry-0.1.0.tar.gz

Download URL agentguard_sentry-0.1.0.tar.gz
Size 19.7 kB
Tags Source
SHA-256 checksum
How to use checksums
f747167f16d608ad490f635f866b426fe60a1d1409486fef6bf89b35e8a12d9a
BLAKE2b-256 checksum
How to use checksums
9f7310a6a4e695323275dd883f756a2009402f5dc63001066d364975b901e7da
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.6

Release files / agentguard_sentry-0.1.0-py3-none-any.whl

Download URL agentguard_sentry-0.1.0-py3-none-any.whl
Size 1.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5694be88024b25ca3138eb5690d989496d79cc32f789d20ffd5497591b0785b3
BLAKE2b-256 checksum
How to use checksums
d583ab0889bb5721a338f623d9b655ed08b11e243765d1d0f9e0b4703058b826
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.6

Security for agentguard-sentry 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

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