GTA AI Agent
by open-compass[NeurIPS 2024 D&B] GTA: A Benchmark for General Tool Agents & [arXiv 2026] GTA-2
GTA is an open-source ai agent by open-compass, written mainly in Python, with 153 GitHub stars and the Apache-2.0 license. Its code was last updated Oct 24, 2026.
Scan summary: scanned Nov 5, 2026 at commit 1fca5d4. 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
1fca5d4 · 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 audit667 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 (111)
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.code-execution 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.
- 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.
- 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.
- 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.Turns off TLS certificate checking, allowing traffic interception.
agentlego/webui/app.py:61 - 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.
agentlego/webui/one_click.py:111 - 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.
opencompass/opencompass/datasets/cibench.py:440 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
opencompass/opencompass/datasets/ds1000.py:256 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
opencompass/opencompass/datasets/ds1000.py:259 - 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.
opencompass/opencompass/datasets/ds1000.py:290 - 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.
opencompass/opencompass/datasets/ds1000.py:295 - 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.
opencompass/opencompass/datasets/lawbench/evaluation_functions/wsjd.py:41 - 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.
opencompass/opencompass/datasets/lawbench/evaluation_functions/wsjd.py:42 - 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.
opencompass/opencompass/datasets/lawbench/evaluation_functions/wsjd.py:43 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Contacts a hard-coded IP address instead of a domain name.
opencompass/opencompass/models/krgpt_api.py:23 - 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.
opencompass/opencompass/runners/local.py:121 - 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.
opencompass/opencompass/runners/local.py:201 - 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.
opencompass/opencompass/runners/local_api.py:207 - 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.
opencompass/opencompass/runners/slurm.py:132 - 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.
opencompass/opencompass/runners/slurm.py:147 - 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.
opencompass/opencompass/runners/slurm_sequential.py:151 - 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.
opencompass/opencompass/runners/slurm_sequential.py:204 - 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.
opencompass/opencompass/runners/slurm_sequential.py:223 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.requests@2.9.2: 5 known vulnerabilitiesPYSEC-2018-28, PYSEC-2023-74, PYSEC-2026-1872, PYSEC-2026-1873, PYSEC-2026-2275
agentlego/examples/visual_chatgpt/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.markdown@3.6: 2 known vulnerabilitiesPYSEC-2026-89, PYSEC-2026-89
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.accelerate@0.29.3: 2 known vulnerabilitiesPYSEC-2026-3804, PYSEC-2026-3804
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.cryptography@42.0.5: 14 known vulnerabilitiesPYSEC-2026-1284, PYSEC-2026-2141, PYSEC-2026-35, PYSEC-2026-3553, PYSEC-2026-3554 +9 more
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.diffusers@0.27.2: 6 known vulnerabilitiesPYSEC-2026-2446, PYSEC-2026-40, PYSEC-2026-41, PYSEC-2026-2446, PYSEC-2026-40 +1 more
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.fsspec@2024.3.1: 3 known vulnerabilitiesPYSEC-2026-4217, PYSEC-2026-4217, PYSEC-2026-4217
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.protobuf@5.26.1: 4 known vulnerabilitiesPYSEC-2026-1805, PYSEC-2026-1806, PYSEC-2026-1805, PYSEC-2026-1806
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.python-multipart@0.0.9: 16 known vulnerabilitiesPYSEC-2026-1851, PYSEC-2026-1852, PYSEC-2026-3036, PYSEC-2026-3037, PYSEC-2026-3038 +11 more
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.sentencepiece@0.2.0: 2 known vulnerabilitiesPYSEC-2026-1909, PYSEC-2026-1909
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.starlette@0.37.2: 14 known vulnerabilitiesPYSEC-2026-161, PYSEC-2026-1941, PYSEC-2026-1943, PYSEC-2026-2280, PYSEC-2026-2281 +9 more
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.urllib3@1.26.18: 16 known vulnerabilitiesPYSEC-2026-141, PYSEC-2026-1994, PYSEC-2026-1995, PYSEC-2026-1996, PYSEC-2026-1998 +11 more
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.markdown@3.6.0: 1 known vulnerabilityPYSEC-2026-89
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.setuptools@60.2.0: 5 known vulnerabilitiesPYSEC-2022-43012, PYSEC-2025-49, PYSEC-2026-1918, PYSEC-2026-3447, GHSA-xmj3-9gf7-h52w
agentlego/requirements_all.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.mako@1.3.10: 3 known vulnerabilitiesPYSEC-2026-2617, PYSEC-2026-4243, PYSEC-2026-88
agentlego/requirements_gta_v2.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.curl-cffi@0.13.0: 1 known vulnerabilityPYSEC-2026-2431
agentlego/requirements_gta_v2.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.lightning@2.5.1.post0: 2 known vulnerabilitiesPYSEC-2026-3624, PYSEC-2026-3972
agentlego/requirements_gta_v2.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.lxml@5.4.0: 1 known vulnerabilityPYSEC-2026-87
agentlego/requirements_gta_v2.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.msgpack@1.1.0: 2 known vulnerabilitiesPYSEC-2026-3625, GHSA-j586-36cw-2gc2
agentlego/requirements_gta_v2.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.pytorch-lightning@2.5.1.post0: 2 known vulnerabilitiesPYSEC-2026-3043, PYSEC-2026-3967
agentlego/requirements_gta_v2.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.soupsieve@2.8.3: 4 known vulnerabilitiesPYSEC-2026-3071, PYSEC-2026-3072, PYSEC-2026-4170, PYSEC-2026-4171
agentlego/requirements_gta_v2.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.accelerate@1.9.0: 1 known vulnerabilityPYSEC-2026-3804
opencompass/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
opencompass/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.transformers@5.9.0: 1 known vulnerabilityPYSEC-2026-3929
opencompass/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
agentlego/docs/en/conf.py:35 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
agentlego/docs/zh_cn/conf.py:35 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
opencompass/docs/en/conf.py:35 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
opencompass/docs/zh_cn/conf.py:35 - lowLow. Minor, or common in normal tools. Shown for information.idna@3.9.0: 3 known vulnerabilitiesPYSEC-2026-215, PYSEC-2026-215, PYSEC-2026-215
agentlego/examples/visual_chatgpt/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.marshmallow@3.9.1: 1 known vulnerabilityPYSEC-2026-1605
agentlego/examples/visual_chatgpt/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.pydantic@1.9.2: 1 known vulnerabilityPYSEC-2026-1812
agentlego/examples/visual_chatgpt/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.pygments@2.17.2: 3 known vulnerabilitiesPYSEC-2026-2987, PYSEC-2026-2987, PYSEC-2026-2987
agentlego/requirements_all.txt - lowLow. Minor, or common in normal tools. Shown for information.fonttools@4.51.0: 2 known vulnerabilitiesPYSEC-2026-1389, PYSEC-2026-1389
agentlego/requirements_all.txt - lowLow. Minor, or common in normal tools. Shown for information.python-dotenv@1.0.1: 2 known vulnerabilitiesPYSEC-2026-2270, PYSEC-2026-2270
agentlego/requirements_all.txt - lowLow. Minor, or common in normal tools. Shown for information.requests@2.28.2: 8 known vulnerabilitiesPYSEC-2023-74, PYSEC-2026-1872, PYSEC-2026-1873, PYSEC-2026-2275, PYSEC-2023-74 +3 more
agentlego/requirements_all.txt - lowLow. Minor, or common in normal tools. Shown for information.scikit-learn@1.4.2: 2 known vulnerabilitiesPYSEC-2024-110, PYSEC-2024-110
agentlego/requirements_all.txt - lowLow. Minor, or common in normal tools. Shown for information.tqdm@4.65.2: 2 known vulnerabilitiesPYSEC-2026-1976, PYSEC-2026-1976
agentlego/requirements_all.txt - lowLow. Minor, or common in normal tools. Shown for information.zipp@3.18.1: 2 known vulnerabilitiesPYSEC-2026-2074, PYSEC-2026-2074
agentlego/requirements_all.txt - lowLow. Minor, or common in normal tools. Shown for information.pypdf2@3.0.1: 1 known vulnerabilityPYSEC-2026-1835
agentlego/requirements_gta_v2.txt - lowLow. Minor, or common in normal tools. Shown for information.filelock@3.18.0: 4 known vulnerabilitiesPYSEC-2026-1374, PYSEC-2026-1375, GHSA-69hj-f68j-2879, GHSA-8mx5-7m5m-r77g
agentlego/requirements_gta_v2.txt - lowLow. Minor, or common in normal tools. Shown for information.idna@3.10: 1 known vulnerabilityPYSEC-2026-215
agentlego/requirements_gta_v2.txt - lowLow. Minor, or common in normal tools. Shown for information.pytest@9.0.2: 1 known vulnerabilityPYSEC-2026-1845
agentlego/requirements_gta_v2.txt - lowLow. Minor, or common in normal tools. Shown for information.datasets@2.19.1: 1 known vulnerabilityPYSEC-2026-3716
opencompass/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.requests@2.31.0: 3 known vulnerabilitiesPYSEC-2026-1872, PYSEC-2026-1873, PYSEC-2026-2275
opencompass/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.scikit-learn@1.2.1: 2 known vulnerabilitiesPYSEC-2024-110, PYSEC-2024-110
opencompass/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.tqdm@4.64.1: 1 known vulnerabilityPYSEC-2026-1976
opencompass/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.scipy@1.9.3: 1 known vulnerabilityPYSEC-2023-102
opencompass/requirements.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.
GTA alternatives
View more →Similar ai agents in Research & Analysis, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| GTA (this page) open-compass | 153 | Apache-2.0 | Oct 24, 2026 | Scanned, no flagged issues |
| Hermes Agent NousResearch | 259k | MIT | Nov 1, 2026 | Scanned, no flagged issues |
| Anything LLM Mintplex-Labs | 68k | MIT | Oct 30, 2026 | Scanned, no flagged issues |
| Khazix Skills KKKKhazix | 22k | MIT | Oct 1, 2026 | Scanned, no flagged issues |
| Hermes Webui nesquena | 19k | MIT | Nov 1, 2026 | Scanned, no flagged issues |
| DocsGPT arc53 | 18k | MIT | Nov 1, 2026 | Scanned, no flagged issues |