The original repository has been deleted or made private. This page is an archival snapshot from indexing time; the install command may no longer work.
Install verification: Ecosystem app: not installed via dsh plugin add, so the L1-L5 plugin install-verification ladder does not apply; the security scan still runs.Install verification details →
Data as of (UTC)
What it doesAI
Browser automation tools for DeepSeek Harness agent, built on Playwright as a Cordis plugin.
- Playwright-based browser automation
- Self-contained Cordis agent-preset plugin
- DeepSeek Harness (DSH) agent tools
Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.
Installation
Ecosystem apps are not installable via dsh plugin add: desktop / web shells install or deploy through their own release channel (GitHub Releases or the project site).
The level reads L5 · Ecosystem plugin / L5 · Ecosystem app per the three-way classification (the L1-L5 ladder does not rate them); the security scan still runs.
Verification & Compatibility◼ Ecosystem app
Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.
External credentials (plugin-level): none detected
| plugin \ dsh | dsh 0.1.5-rc.2 | dsh 0.1.3-alpha.2 | dsh 0.1.3-alpha.1 | dsh 0.1.2-rc.1 | dsh 0.1.2-alpha.1 |
|---|---|---|---|---|---|
| v0.1.0 | · | ◼ | ◼ | · | · |
v0.1.0github◼ 2 ecosystem app2026-09-11
https://github.com/momo-gen/dsh-browser-pilot
◼dsh 0.1.3-alpha.22026-09-08Ecosystem app
- • Node.js: v24.14.0
- • DSH: 0.1.3-alpha.2
- • Plugin artifact: github · https://github.com/momo-gen/dsh-browser-pilot#v0.1.0
ID: dsh-browser-pilot@v0.1.0@dsh0.1.3-alpha.2 · profile: l4-sandbox
Issued: 2026-09-08 · expires: 2026-09-15
View checks & evidence
not present in web-profile loader inventory
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
◼dsh 0.1.3-alpha.12026-09-07Ecosystem app
- • Node.js: v24.14.0
- • DSH: 0.1.3-alpha.1
- • Plugin artifact: github · https://github.com/momo-gen/dsh-browser-pilot#v0.1.0
ID: dsh-browser-pilot@v0.1.0@dsh0.1.3-alpha.1 · profile: l4-sandbox
Issued: 2026-09-07 · expires: 2026-09-14
View checks & evidence
not present in web-profile loader inventory
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).
Author badges
Embed the dsh.so badges in your README to show this plugin's automated security-scan and install-test status:
`[](https://www.dsh.so/artifact/dsh-browser-pilot/?ref=badge)`dsh.so is an independent community project, not affiliated with or endorsed by DeepSeek AI. Badges are maintained by dsh.so; embed links carry a ?ref= attribution parameter.
Security Report
Two automated layers, neither a manual review: a static scan (per-plugin rule checks) and a model-driven dynamic security audit that covers only the subset static-flagged at warn or above and never executes plugin code.
Static high; dynamic low (authoritative when present) → overall low.
v0.1.0v0.1.0git2026-09-12v0.1.0same versionsuspicious · gitVet is an AST static scan (npm artifact or git source).
show static findings (4)
- criticalnewFunction · code-exec
src/browser.ts:147const fn = new Function(`return (${expression})`) as () => unknown - warningmanifest-fs-unfenced · sandbox
agent.cordis.ymlMutating filesystem tool has no explicit fs backend in realm - warningmanifest-search-unfenced · sandbox
agent.cordis.ymlSearch tool reads without an explicit fs mount - warningmanifest-shell-unfenced · sandbox
agent.cordis.ymlShell tool without a sandbox runner or policy in realm
show 2 audit findings
- lowbrowser_evaluate compiles the model-supplied expression with new Function, but Playwright runs it only in the page, never in the Node host
src/browser.ts:147The 'critical code-exec' signal is refuted for the host: `new Function` only compiles the string into a function object; the object is handed to page.evaluate, which serializes it and evaluates it inside the browser sandbox, so no host-process code runs (constructing the Function also evaluates nothing, and the injected body cannot escape because the wrapper is never called in Node). The residual risk is conditional and opt-in: with allowEvaluate: true, model-supplied JavaScript executes in whatever origin the page has navigated to, allowing same-origin reads, DOM/session manipulation and exfi
- lowURL guard validates only the scheme, so the agent can navigate to localhost, private ranges and cloud metadata endpoints (SSRF)
src/guard.ts:84assertSafeUrl blocks dangerous schemes but performs no host/IP filtering, so an agent (or content that prompt-injects the agent) can call browser_navigate with http://127.0.0.1:*, http://169.254.169.254/... or other internal hosts and read the responses via browser_html/browser_text, turning the host's network position into a data-exfiltration path. Exploitation requires the model to choose such a URL, so this is an inherent capability of a browsing tool rather than an attacker-controlled primitive.
Playwright browser tools with scheme allow-list, workspace-confined output paths and opt-in evaluate; the static code-exec hit is a false positive because new Function is never invoked in the Node host.
Rule (2026-10-28): when a dynamic conclusion exists it is authoritative (it may raise or lower the level); the static scan tier (vet primary, dsh backstop) applies only when there is none (not queued / audit failed / withdrawn). The audit never writes the exemption list (exemptions are manual only); a wrong conclusion is withdrawn by human review and the tier falls back to the static scan tier.
Disclaimer: the static scan and the dynamic security audit are both automated analysis, not a security guarantee. Always review what you install.
Activity
Last commit 2026-08-14 · activity: Inactive
• Repo created: 2026-08-18
• Stars: ★ 1 · Forks: 0
• Health: Inactive — no commit in 90+ days
Source
Author README
View on GitHub ↗The author's original README from the repository — fetched live, unedited (the English page loads the default README).
Frequently asked questions
What is dsh-browser-pilot?
dsh-browser-pilot is an ecosystem app listed on dsh.so, not a DSH plugin package: it cannot be installed with dsh plugin add and ships through the project's own release channel.
Is dsh.so or this plugin page official?
dsh.so is an independent community registry and is not affiliated with, endorsed by, or sponsored by DeepSeek AI.
How do I install dsh-browser-pilot?
This is an ecosystem app, not a plugin installable via dsh plugin add: desktop / web shells install or deploy through their own release channel. The security scan still runs, but the L1-L5 plugin install ladder does not rate it.
How does the security scan relate to a manual audit?
Both layers are automated, not a manual audit. The static scan is heuristic analysis of the repository source, so it can produce false positives and miss context. The model-driven dynamic security audit only covers plugins static-flagged at warn or above, never executes plugin code, and its conclusion is authoritative when there is one (it may raise or lower the static tier); exemptions stay manual. Neither layer is an endorsement: review the repository and the permissions it asks for before installing, together with the verification level and health signals.
How fresh is the data on this page?
The data on this page is as of 2026-10-17 (UTC) — the most recent valid timestamp among the registry refresh, install verification, security scan and dynamic audit. Build time is never used as a data date.
