Agent Framework
by microsoftA framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Agent Framework is an open-source ai agent by microsoft, written mainly in Python, with 14,467 GitHub stars and the MIT license. Its code was last updated Oct 30, 2026.
Scan summary: scanned Nov 5, 2026 at commit 07b9b3f. Seen able to run shell commands, run dynamic code, connect to the internet. Scan policy
ScannedScanned. The automated checks below ran on the commit shown. Read each line for what was and was not covered.
Full scan at
07b9b3f · Nov 5, 2026 ScannedStatic, secrets and dependency checks completed with no critical findings.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.Static code scanwarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Flagged. This check found an issue. See the findings below.Secrets scanfailFlagged. This check found an issue. See the findings below.
Flagged. This check found an issue. See the findings below.Dependency audit201 known vulnerabilitiesfailFlagged. This check found an issue. See the findings below.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.ManifestnonewarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Buildn/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Boot & handshaken/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Network egressn/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Reproducible (×3)n/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Findings (25)
- highHigh. Something risky that needs a close look before you install.secrets issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.secrets issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.secrets issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.secrets issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dependencies issueDetails are available to the maintainer after claiming this listing.
- mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
python/packages/core/agent_framework/_workflows/_checkpoint_encoding.py:517 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.zod@4.6.5: 2 known vulnerabilitiesGHSA-mrhx-c7xc-m3w5, GHSA-mrhx-c7xc-m3w5
python/packages/devui/frontend/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.filelock@3.32.7: 13 known vulnerabilitiesGHSA-567q-5qvw-pf92, GHSA-6627-m3xw-93mp, GHSA-69hj-f68j-2879, GHSA-8mx5-7m5m-r77g, GHSA-9c4x-gm8v-wgc4 +8 more
python/packages/lab/uv.lock - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.httpcore2@2.9.1: 12 known vulnerabilitiesPYSEC-2026-3844, PYSEC-2026-3844, PYSEC-2026-3844, PYSEC-2026-3844, PYSEC-2026-3844 +7 more
python/samples/02-agents/harness/build_your_own_claw/claw_step04_production_ready/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.httpx2@2.9.1: 60 known vulnerabilitiesPYSEC-2026-3845, PYSEC-2026-3846, PYSEC-2026-3847, PYSEC-2026-3848, PYSEC-2026-3849 +55 more
python/samples/02-agents/harness/build_your_own_claw/claw_step04_production_ready/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.python-multipart@0.0.9: 96 known vulnerabilitiesPYSEC-2026-1851, PYSEC-2026-1852, PYSEC-2026-3036, PYSEC-2026-3037, PYSEC-2026-3038 +91 more
python/samples/02-agents/harness/build_your_own_claw/claw_step04_production_ready/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.pyasn1@0.6.4: 4 known vulnerabilitiesGHSA-2qm8-x737-gmw5, GHSA-9m75-vc3g-4x39, GHSA-fm9c-5rcf-2q5p, GHSA-mm57-4v3p-rchx
python/uv.lock - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
python/samples/02-agents/providers/anthropic/anthropic_with_shell.py:32 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Sends data to a paste site, webhook catcher or chat webhook — common exfiltration channels.
python/samples/04-hosting/foundry-hosted-agents/invocations/telegram/main.py:210 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
python/samples/04-hosting/foundry-hosted-agents/responses/tools/main.py:48 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Sends data to a paste site, webhook catcher or chat webhook — common exfiltration channels.
python/samples/05-end-to-end/chatkit-integration/frontend/vite.config.ts:20 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
dotnet/tests/Microsoft.Agents.AI.CosmosNoSql.UnitTests/CosmosChatHistoryProviderMaxBatchSizeTests.cs:14 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
python/packages/azure-cosmos-memory/tests/test_emulator.py:43 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
python/packages/anthropic/tests/conftest.py:30 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
python/packages/anthropic/tests/test_anthropic_client.py:89 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key2 matches in this file
python/packages/core/tests/core/test_as_tool_kwargs_propagation.py:62 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: curl-auth-header
python/samples/02-agents/context_providers/azure_ai_search/README.md:204 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
python/samples/04-hosting/foundry-hosted-agents/responses/azure_search_rag/README.md:183 - lowLow. Minor, or common in normal tools. Shown for information.minimatch@10.2.6: 2 known vulnerabilitiesGHSA-g3hv-75wg-m249, GHSA-g3hv-75wg-m249
python/packages/devui/frontend/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.No manifest declaring network access and environment variables (agent.json)
Automated result for the commit shown. See our scan policy. View the scan log
Maintainers can claim the listing to rescan, or dispute a result.
Agent Framework alternatives
View more →Similar ai agents in Developer Tools, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Agent Framework (this page) microsoft | 14k | MIT | Oct 30, 2026 | Scanned, no flagged issues |
| Deepseek Harness deepseek-ai | 268k | MIT | Oct 30, 2026 | Scanned, no flagged issues |
| Ponytail DietrichGebert | 182k | MIT | Oct 29, 2026 | Scanned, no flagged issues |
| Orca stablyai | 112k | MIT | Nov 1, 2026 | Scanned, no flagged issues |
| Deer Flow bytedance | 85k | MIT | Nov 1, 2026 | Scanned, no flagged issues |
| Ruflo ruvnet | 80k | MIT | Nov 1, 2026 | Scanned, no flagged issues |