Loushang Agent Skill

by zhnt• 1.9k•• Scanned•Claim this listing•Request removal
Coding Agentsagentagent harnessagenticaichatgpt

AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.

Loushang is an open-source agent skill by zhnt, written mainly in Python, with 1,939 GitHub stars and the Apache-2.0 license. Its code was last updated Nov 1, 2026.

Scan summary: scanned Nov 5, 2026 at commit 739f947. Seen able to run shell commands, read environment and secrets, connect to the internet. Scan policy

Scanned
Full scan at 739f947 · Nov 5, 2026
Scanned Builds
Static code scanwarn
Secrets scanfail
Dependency audit90 known vulnerabilitiesfail
Manifestnonewarn
Buildpass
Boot & handshaken/a
Network egresswarn
Reproducible (×3)n/a

Findings (56)

  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    credential-access issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    exfiltration issue
    Details are available to the maintainer after claiming this listing.
  • high
    secrets issue
    Details are available to the maintainer after claiming this listing.
  • high
    secrets issue
    Details are available to the maintainer after claiming this listing.
  • high
    secrets issue
    Details are available to the maintainer after claiming this listing.
  • high
    secrets issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    src/loushang/harness/config/subprocess_values.py:65
  • medium
    source-map-js@1.2.1: 1 known vulnerability
    GHSA-68fv-2mgg-jv7q
    gui/package-lock.json
  • medium
    vite@8.2.2: 6 known vulnerabilities
    GHSA-587h-7wmj-h5pm, GHSA-698v-4r3x-3vcv, GHSA-9jrq-w75r-8gcw, GHSA-r825-w8mm-5pxw, GHSA-rq7h-c2jc-7f22 +1 more
    gui/package-lock.json
  • medium
    cryptography@48.0.1: 3 known vulnerabilities
    PYSEC-2026-3552, PYSEC-2026-3553, PYSEC-2026-3554
    uv.lock
  • medium
    joserfc@1.7.4: 2 known vulnerabilities
    GHSA-9pg5-8c7x-5hfx, GHSA-jpxq-7h8p-2q76
    uv.lock
  • medium
    Install contacted hosts other than package registries
    releases.astral.sh
  • low
    Possible example credential in docs/tests: generic-api-key
    docs/internals/architecture/appserver/detachable-local-workspace-g16-inventory.json:42
  • low
    Possible example credential in docs/tests: generic-api-key
    docs/internals/architecture/apphost/hosted-session-workflow-g17.md:1607
  • low
    Possible example credential in docs/tests: generic-api-key
    tests/apphost/test_contracts.py:325
  • low
    Possible example credential in docs/tests: generic-api-key
    tests/architecture/test_hosting_h6_windows_native.py:51
  • low
    Possible example credential in docs/tests: generic-api-key
    tests/coding/fixtures/goal_refactor_v1/manifest.json:9
  • low
    Possible example credential in docs/tests: generic-api-key
    tests/harness/host/test_rpc_plugin_desired.py:188
  • low
    Possible example credential in docs/tests: curl-auth-header
    tests/harness/test_approval_projection.py:45
  • low
    Possible example credential in docs/tests: curl-auth-header
    tests/harness/tools/test_authorization_gateway.py:604
  • low
    Possible example credential in docs/tests: generic-api-key
    tests/hosting/test_windows_launch_preparation.py:86
  • low
    @vitest/mocker@4.1.11: 2 known vulnerabilities
    GHSA-qxg6-89mg-rqv8, GHSA-xp26-3454-mjgp
    gui/package-lock.json
  • low
    glib@0.18.5: 1 known vulnerability
    RUSTSEC-2024-0429
    gui/src-tauri/Cargo.lock
  • low
    proc-macro-error@1.0.4: 1 known vulnerability
    RUSTSEC-2024-0370
    gui/src-tauri/Cargo.lock
  • low
    tokio@1.53.1: 1 known vulnerability
    RUSTSEC-2026-0386
    gui/src-tauri/Cargo.lock
  • low
    unic-char-property@0.9.0: 1 known vulnerability
    RUSTSEC-2025-0081
    gui/src-tauri/Cargo.lock
  • low
    unic-char-range@0.9.0: 1 known vulnerability
    RUSTSEC-2025-0075
    gui/src-tauri/Cargo.lock
  • low
    unic-common@0.9.0: 1 known vulnerability
    RUSTSEC-2025-0080
    gui/src-tauri/Cargo.lock
  • low
    unic-ucd-ident@0.9.0: 1 known vulnerability
    RUSTSEC-2025-0100
    gui/src-tauri/Cargo.lock
  • low
    unic-ucd-version@0.9.0: 1 known vulnerability
    RUSTSEC-2025-0098
    gui/src-tauri/Cargo.lock
  • low
    idna@3.11: 1 known vulnerability
    PYSEC-2026-215
    uv.lock
  • low
    pytest@8.4.2: 1 known vulnerability
    PYSEC-2026-1845
    uv.lock
  • low
    No manifest declaring network access and environment variables (agent.json)

Network activity

During install
files.pythonhosted.orgpypi.orgreleases.astral.sh
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.

Loushang alternatives

View more →

Similar agent skills in Coding Agents, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
Loushang (this page)
zhnt
1.9kApache-2.0Nov 1, 2026Scanned, no flagged issues
Rea
morluto
417kMITNov 1, 2026Scanned, no flagged issues
Agent Skills
addyosmani
112kMITOct 31, 2026Scanned, no flagged issues
I Have Adhd
ayghri
60kMITOct 19, 2026Scanned, no flagged issues
Open Code Review
alibaba
49kApache-2.0Oct 30, 2026Scanned, no flagged issues
Agent Skills For Context Engineering
muratcankoylan
18kMITOct 12, 2026Scanned, no flagged issues