Mantis AI Agent
by googleA modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
Mantis is an open-source ai agent by google, written mainly in Python, with 2,688 GitHub stars and the Apache-2.0 license. Its code was last updated Oct 30, 2026.
Scan summary: scanned Nov 5, 2026 at commit 89f4004. Seen able to run shell commands, run dynamic code, read environment and secrets, 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
89f4004 · 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 audit9 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 (19)
- highHigh. Something risky that needs a close look before you install.credential-access issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.credential-access issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.credential-access issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.credential-access 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.credential-access 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.Contacts a hard-coded IP address instead of a domain name.
reference/core/environments/gce_env.py:44 - 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.
reference/evals/research_target/admintools.py:12 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Deserializes data with pickle/marshal, which can execute code.
reference/evals/research_target/dal/cache.py:24 - 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.
reference/test_targets/app.py:78 - 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.
reference/test_targets/vault_app.py:78 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: slack-bot-token
reference/tests/test_adk_invariants.py:769 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: github-pat
reference/tests/test_adk_invariants.py:770 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
reference/tests/test_security_regression.py:8899 - lowLow. Minor, or common in normal tools. Shown for information.opentelemetry-api@1.42.1: 1 known vulnerabilityGHSA-xcq7-p3pf-p88h
reference/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.
Mantis alternatives
View more →Similar ai agents in Security & Testing, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Mantis (this page) google | 2.7k | Apache-2.0 | Oct 30, 2026 | Scanned, no flagged issues |
| ECC affaan-m | 294k | MIT | Oct 30, 2026 | Scanned, no flagged issues |
| Strix usestrix | 73k | Apache-2.0 | Oct 30, 2026 | Scanned, no flagged issues |
| Goose aaif-goose | 56k | Apache-2.0 | Nov 1, 2026 | Scanned, no flagged issues |
| Anthropic Cybersecurity Skills mukul975 | 35k | Apache-2.0 | Aug 31, 2026 | Scanned, no flagged issues |
| Pentagi vxcontrol | 33k | MIT | Oct 22, 2026 | Scanned, no flagged issues |