Hands On LLM AI Agent
by FRS2003动手学大模型全栈：CS336 中文精讲 · PyTorch 手搓 Transformer · 单卡复现 Pretrain/SFT/LoRA/DPO/GRPO/RLVR · PEFT/Agent/RAG 落地（含真实实验、曲线与复现脚本）
Hands On LLM is an open-source ai agent by FRS2003, written mainly in Python, with 121 GitHub stars and the MIT license. Its code was last updated Sep 16, 2026.
Scan summary: scanned Nov 5, 2026 at commit a828c96. Seen able to run shell commands, run dynamic code. 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
a828c96 · 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.
Passed. This check ran and found nothing it flags.Secrets scanpassPassed. This check ran and found nothing it flags.
Flagged. This check found an issue. See the findings below.Dependency audit258 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 (67)
- highHigh. Something risky that needs a close look before you install.dependencies 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.
- highHigh. Something risky that needs a close look before you install.dependencies 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.
- highHigh. Something risky that needs a close look before you install.dependencies 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.Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
04-agent/tools.py:149 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/agent/tools.py:43 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/agent/tools.py:45 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/app/app.py:30 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/app/app.py:32 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/app_v2.py:31 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/app_v2.py:33 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/bench_hybrid2.py:13 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/bench_hybrid2.py:15 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_en.py:13 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_en.py:15 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_final.py:13 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_final.py:15 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_fix.py:13 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_fix.py:15 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_pmc.py:13 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_pmc.py:15 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_reranker.py:13 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_reranker.py:15 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_v2.py:13 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/benchmark_v2.py:15 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/reranker_bench.py:12 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/reranker_bench.py:13 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/utils/check_abstracts.py:3 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/utils/check_abstracts.py:5 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/utils/check_lang.py:3 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/utils/check_rank_llm.py:9 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/utils/debug_q3.py:9 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/utils/debug_q3.py:10 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/evaluation/benchmark_hybrid.py:14 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/evaluation/benchmark_hybrid.py:16 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/evaluation/benchmark_qe.py:17 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
05-rag-application/evaluation/benchmark_qe.py:19 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.accelerate@1.7.0: 1 known vulnerabilityPYSEC-2026-3804
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.aiohttp@3.14.3: 8 known vulnerabilitiesGHSA-2g87-pp6c-29x5, GHSA-494j-54xm-rwp3, GHSA-5wr8-gcqf-gqf3, GHSA-6cjc-53gc-5rqm, GHSA-9xw5-w5jj-pvcg +3 more
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.filelock@3.32.6: 13 known vulnerabilitiesGHSA-567q-5qvw-pf92, GHSA-6627-m3xw-93mp, GHSA-69hj-f68j-2879, GHSA-8mx5-7m5m-r77g, GHSA-9c4x-gm8v-wgc4 +8 more
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.fsspec@2025.3.0: 1 known vulnerabilityPYSEC-2026-4217
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.gradio@5.31.0: 7 known vulnerabilitiesPYSEC-2026-211, PYSEC-2026-2178, PYSEC-2026-2179, PYSEC-2026-63, PYSEC-2026-64 +2 more
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.llamafactory@0.9.3: 2 known vulnerabilitiesPYSEC-2026-1573, PYSEC-2026-1576
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.msgpack@1.2.2: 1 known vulnerabilityGHSA-j586-36cw-2gc2
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.nltk@3.10.3: 2 known vulnerabilitiesGHSA-8mgp-746c-j5xp, GHSA-j456-xh4h-cpf2
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.starlette@0.52.1: 5 known vulnerabilitiesPYSEC-2026-161, PYSEC-2026-2280, PYSEC-2026-2281, PYSEC-2026-248, PYSEC-2026-249
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.torch@2.6.0: 22 known vulnerabilitiesPYSEC-2025-191, PYSEC-2025-198, PYSEC-2025-199, PYSEC-2025-200, PYSEC-2025-201 +17 more
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.urllib3@2.7.0: 3 known vulnerabilitiesPYSEC-2026-4175, PYSEC-2026-4176, PYSEC-2026-4177
03-peft-framework/experiments/peft_lab/requirements-lock.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.httpcore2@2.9.1: 2 known vulnerabilitiesPYSEC-2026-3844, PYSEC-2026-3844
04-agent/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.httpx2@2.9.1: 10 known vulnerabilitiesPYSEC-2026-3845, PYSEC-2026-3846, PYSEC-2026-3847, PYSEC-2026-3848, PYSEC-2026-3849 +5 more
04-agent/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.torch@2.9.1: 4 known vulnerabilitiesPYSEC-2026-139, PYSEC-2026-2286, GHSA-qfhq-4f3w-5fph, GHSA-rrmf-rvhw-rf47
05-rag-application/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.accelerate@1.9.0: 1 known vulnerabilityPYSEC-2026-3804
05-rag-application/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.transformers@5.9.0: 1 known vulnerabilityPYSEC-2026-3929
05-rag-application/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Downloads a script and pipes it straight into a shell (often an installer command shown to users; check where it runs).
04-agent/test_full.py:86 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/test_retrieval.py:13 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/test_retrieval.py:14 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/test_variants.py:9 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
05-rag-application/archive/process-scripts/evaluation/test_variants.py:10 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
05-rag-application/evaluation/test_hyde.py:13 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
05-rag-application/evaluation/test_hyde.py:14 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
05-rag-application/evaluation/test_qe_split.py:13 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
05-rag-application/evaluation/test_qe_split.py:14 - lowLow. Minor, or common in normal tools. Shown for information.datasets@3.6.0: 1 known vulnerabilityPYSEC-2026-3716
03-peft-framework/experiments/peft_lab/requirements-lock.txt - lowLow. Minor, or common in normal tools. Shown for information.multidict@6.8.0: 1 known vulnerabilityPYSEC-2026-4244
03-peft-framework/experiments/peft_lab/requirements-lock.txt - 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.
Hands On LLM alternatives
View more →Similar ai agents in Data Science & ML, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Hands On LLM (this page) FRS2003 | 121 | MIT | Sep 16, 2026 | Scanned, no flagged issues |
| Ragflow infiniflow | 93k | Apache-2.0 | Oct 31, 2026 | Scanned, no flagged issues |
| Cherry Studio CherryHQ | 53k | AGPL-3.0 | Nov 1, 2026 | Scanned, no flagged issues |
| PageIndex VectifyAI | 40k | MIT | Oct 29, 2026 | Scanned, no flagged issues |
| Graphiti getzep | 32k | Apache-2.0 | Nov 1, 2026 | Scanned, no flagged issues |
| Cua trycua | 31k | MIT | Nov 1, 2026 | Scanned, no flagged issues |