Metaharness AI Agent
by ruvnet🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
Metaharness is an open-source ai agent by ruvnet, written mainly in TypeScript, with 735 GitHub stars and the MIT license. Its code was last updated Nov 1, 2026.
Scan summary: scanned Nov 5, 2026 at commit 2f415bf. Seen able to run shell commands, 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
2f415bf · 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 audit120 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.
Flagged. This check found an issue. See the findings below.BuildfailFlagged. This check found an issue. See the findings below.
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.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.Network egresswarnWarning. 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.Reproducible (×3)n/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Findings (82)
- highHigh. Something risky that needs a close look before you install.dropper issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.backdoor issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.backdoor issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.backdoor issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.backdoor issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dropper 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.dropper issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dropper issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dropper issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dropper 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.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.
- 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.
packages/horizon/src/executor.ts:123 - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.browserslist@4.28.2: 2 known vulnerabilitiesGHSA-73wf-gq98-2v4g, GHSA-c83g-rgw3-j3cx
apps/web-ui/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.nanoid@3.3.17: 1 known vulnerabilityGHSA-2v37-7h3g-55p8
apps/web-ui/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.source-map-js@1.2.1: 2 known vulnerabilitiesGHSA-68fv-2mgg-jv7q, GHSA-68fv-2mgg-jv7q
apps/web-ui/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.vite@8.2.1: 6 known vulnerabilitiesGHSA-587h-7wmj-h5pm, GHSA-698v-4r3x-3vcv, GHSA-9jrq-w75r-8gcw, GHSA-r825-w8mm-5pxw, GHSA-rq7h-c2jc-7f22 +1 more
apps/web-ui/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.httpcore2@2.9.1: 1 known vulnerabilityPYSEC-2026-3844
packages/darwin-mode/bench/terminal-bench/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.httpx2@2.9.1: 5 known vulnerabilitiesPYSEC-2026-3845, PYSEC-2026-3846, PYSEC-2026-3847, PYSEC-2026-3848, PYSEC-2026-3849
packages/darwin-mode/bench/terminal-bench/requirements.txt - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.body-parser@1.20.5: 2 known vulnerabilitiesGHSA-27r3-jxmh-p828, GHSA-v422-hmwv-36x6
services/apicompletions/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.brace-expansion@2.1.1: 6 known vulnerabilitiesGHSA-3jxr-9vmj-r5cp, GHSA-6j4f-fj2g-mc7p, GHSA-mh99-v99m-4gvg, GHSA-q2hr-2g5m-vwhr, GHSA-qhr7-859c-m2p7 +1 more
services/apicompletions/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.brace-expansion@5.0.7: 5 known vulnerabilitiesGHSA-6j4f-fj2g-mc7p, GHSA-mh99-v99m-4gvg, GHSA-q2hr-2g5m-vwhr, GHSA-qhr7-859c-m2p7, GHSA-rgw5-rvv9-x895
services/apicompletions/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.nanoid@3.3.15: 2 known vulnerabilitiesGHSA-28wg-ghj8-5hjv, GHSA-2v37-7h3g-55p8
services/apicompletions/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.postcss@8.5.16: 2 known vulnerabilitiesGHSA-fxqj-rqcc-2cmp, GHSA-r28c-9q8g-f849
services/apicompletions/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.vite@5.4.21: 8 known vulnerabilitiesGHSA-4w7w-66w2-5vf9, GHSA-587h-7wmj-h5pm, GHSA-698v-4r3x-3vcv, GHSA-9jrq-w75r-8gcw, GHSA-fx2h-pf6j-xcff +3 more
services/apicompletions/package-lock.json - mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Install or build failed in a clean environmentis might be a permissions issue, please double-check the npm error permissions of the file and its containing directories, or try running npm error the command again as root/Administrator. npm error A complete log of this run can be found in: /tmp/home/.npm/_logs/2026-11-05T20_18_53_237Z-debug-0.log
- mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Install contacted hosts other than package registriesbuf.build
- 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).
apps/web-ui/src/generator/__tests__/scaffold.test.ts:147 - 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).
apps/web-ui/src/generator/__tests__/scaffold.test.ts:153 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / new Function / vm).
packages/create-agent-harness/__tests__/generated-templates.test.ts:174 - 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).
packages/create-agent-harness/__tests__/host-config.test.ts:93 - 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).
packages/create-agent-harness/__tests__/host-config.test.ts:102 - 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).
packages/darwin-mode/__tests__/security/inspect-bypass.test.ts:173 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
packages/darwin-mode/bench/security/fixtures/cwe-bench/vuln/eval.py:1 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
packages/darwin-mode/bench/security/fixtures/cwe-bench/vuln/exec.py:1 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
packages/darwin-mode/bench/security/fixtures/cwe-bench/vuln/load_pickle.py:2 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
packages/darwin-mode/bench/security/fixtures/cwe-bench/vuln/load_yaml.py:2 - 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.
packages/darwin-mode/bench/security/fixtures/cwe-bench/vuln/os_system.py:2 - 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.
packages/darwin-mode/bench/security/fixtures/cwe-bench/vuln/shell.py:2 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
packages/darwin-mode/bench/security/fixtures/semgrep-corpus/vuln/eval.py:2 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
packages/darwin-mode/bench/security/fixtures/semgrep-corpus/vuln/exec.py:2 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
packages/darwin-mode/bench/security/fixtures/semgrep-corpus/vuln/load_pickle.py:3 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
packages/darwin-mode/bench/security/fixtures/semgrep-corpus/vuln/load_yaml.py:3 - 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.
packages/darwin-mode/bench/security/fixtures/semgrep-corpus/vuln/shell.py:3 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
packages/darwin-mode/bench/security/fixtures/semgrep/vuln/inj.py:4 - 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).
packages/horizon/__tests__/horizon.test.ts:95 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Touches a sensitive credential location (SSH keys, cloud credentials, browser data or wallets). Expected for some tools, such as browser automation; check why.
packages/horizon/__tests__/horizon.test.ts:103 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Contacts a hard-coded IP address instead of a domain name.
packages/horizon/__tests__/horizon.test.ts:111 - 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).
packages/host-github-actions/__tests__/github-actions.test.ts:191 - 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).
packages/host-github-actions/__tests__/github-actions.test.ts:196 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Executes dynamically built code (eval / exec).
packages/projects/bench/fixtures/planted-vulns/calc_view.py:5 - 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.
packages/projects/bench/fixtures/planted-vulns/net_tools.py:6 - lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Deserializes data with pickle/marshal, which can execute code.
packages/projects/bench/fixtures/planted-vulns/state_loader.py:5 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key2 matches in this file
packages/create-agent-harness/__tests__/redact.test.ts:18 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: jwt
packages/create-agent-harness/__tests__/redact.test.ts:19 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key3 matches in this file
packages/arc-agi-3/__tests__/avo-loop.test.ts:883 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
packages/darwin-mode/__tests__/security/sandbox-injection.test.ts:66 - lowLow. Minor, or common in normal tools. Shown for information.@vitest/mocker@4.1.10: 2 known vulnerabilitiesGHSA-82fw-gwwq-j7x9, GHSA-qxg6-89mg-rqv8
apps/web-ui/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.baseline-browser-mapping@2.10.37: 1 known vulnerabilityGHSA-w5vr-8v7q-w6rv
apps/web-ui/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.postcss-selector-parser@6.1.4: 1 known vulnerabilityGHSA-rj75-hqrm-r3gf
apps/web-ui/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.vitest@4.1.10: 1 known vulnerabilityGHSA-82fw-gwwq-j7x9
apps/web-ui/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.glob@13.0.6: 1 known vulnerabilityGHSA-3g3m-2fjr-6pw4
package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.minimatch@10.2.6: 1 known vulnerabilityGHSA-g3hv-75wg-m249
package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.idna@3.9.0: 1 known vulnerabilityPYSEC-2026-215
packages/arc-agi-3/python/requirements.txt - lowLow. Minor, or common in normal tools. Shown for information.@vitest/mocker@2.1.9: 2 known vulnerabilitiesGHSA-82fw-gwwq-j7x9, GHSA-qxg6-89mg-rqv8
services/apicompletions/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.esbuild@0.21.5: 1 known vulnerabilityGHSA-67mh-4wv8-2f99
services/apicompletions/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.glob@10.5.0: 1 known vulnerabilityGHSA-3g3m-2fjr-6pw4
services/apicompletions/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.minimatch@10.2.5: 1 known vulnerabilityGHSA-g3hv-75wg-m249
services/apicompletions/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.minimatch@9.0.9: 1 known vulnerabilityGHSA-g3hv-75wg-m249
services/apicompletions/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.qs@6.15.3: 3 known vulnerabilitiesGHSA-4mjr-xmp4-gh2g, GHSA-6pq8-jhm2-2vcw, GHSA-x5fp-wj9c-mxmx
services/apicompletions/package-lock.json - lowLow. Minor, or common in normal tools. Shown for information.No manifest declaring network access and environment variables (agent.json)
Network activity
During install
buf.buildregistry.npmjs.org
While running
Not run — the code wasn't started in this scan
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.
Metaharness 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 |
|---|---|---|---|---|
| Metaharness (this page) ruvnet | 735 | MIT | Nov 1, 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 |