Puppeteer

# Fix list: Puppeteer

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/puppeteer, the October 2026 research run, assessed 14 October 2026. Grade BB, 70.6 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Puppeteer: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Security & auth, 52 out of 100, up to 8.4 more on the total

Why it scored 52: No credential to leak and nothing to scope, so the middle band (20 of 30). Chrome's sandbox stays on unless the script turns it off, and request interception can block hosts. There is no allowlist on by default and no confirmation step (8 of 20). Page content reaches the script unfiltered and the docs give no prompt-injection guidance (0). Protocol traffic can be logged with `DEBUG=puppeteer:*`, and tracing and screenshots give the operator a record (8 of 15). SECURITY.md routes reports through Chromium's process, which has a reward programme, an OpenSSF Scorecards workflow runs daily, and no repository advisories were found (16 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 2. Agent ergonomics, 67 out of 100, up to 5.4 more on the total

Why it scored 67: A library adds no tool definitions to context. `page.accessibility.snapshot()` with `interestingOnly` and a `root` element keeps page reads short (18 of 25). Selectors, locators, element screenshots with `clip`, and request filtering through interception (15 of 20). Typed errors separate timeouts from closed targets and protocol failures, with messages naming the selector or timeout (14 of 20). Locators wait for visibility and stability and retry actions. No annotations or idempotency concept apply (10 of 20). `launch()` works with defaults and a bundled browser. JavaScript and TypeScript only (10 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 3. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: Free, self-hosted, nothing to buy, so 20 + 20 + 20 under the self-hosted rule. No payment protocol (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 4. Reliability, 80 out of 100, up to 4 more on the total

Why it scored 80: Scored as local software. Official npm packages `puppeteer` and `puppeteer-core` at 25.13.0, with Node.js 22.12 or later stated in `engines` and a browser support table (20). Public CI runs Chrome and Firefox tests on Linux, macOS and Windows. Of the 20 most recent CI runs on main, 7 to 13 October 2026, 10 concluded in failure, the newest in Windows headful Firefox and Chrome pipe jobs (12 of 25). 272 open issues and pull requests. Confirmed bugs carry P2 or P3 labels, several without a reply, such as `page.goto()` ignoring its timeout after a second navigation (18 of 25). release-please with conventional commits, breaking changes under their own heading and a major version for each set (15). Version 25, stable (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 5. Schema & documentation, 81 out of 100, up to 3.1 more on the total

Why it scored 81: Graded as a library. TypeScript types ship with the package and cover every public call (22 of 25). No llms.txt and no Markdown routes on pptr.dev, though the docs and the 643-page API reference are Markdown in the repository (5 of 10). TSDoc on each member with remarks and parameter descriptions. Guides explain when to use locators or `page.$()`, with few statements of when not to use a call (14 of 20). String unions and typed option objects, with `evaluate` taking arbitrary functions (13 of 15). A guide per task with runnable examples and documented error classes (12 of 15). Versioned releases and a changelog for each (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 6. Transparency & trust, 70 out of 100, up to 2.6 more on the total

Made of editorial 72, provenance 68.

Why it scored 70: Apache-2.0, published by Google (30). No data statement for the library. It runs locally, downloads browsers from Google's storage at install, and the docs say where browsers are cached (18 of 30). Each release lists breaking changes, deprecated APIs are marked in the reference, and the support table maps versions to browsers. No written deprecation policy (10 of 20). No telemetry found in the library source, and the docs do not say so either way (14 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: pptr.dev, registered 2018-05-23 (8 years) (11 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 89 out of 100, up to 1 more on the total

Why it scored 89: 25.13.0 on 8 October 2026 (30). Ten releases since 27 July 2026 (20). Confirmed bugs are labelled and pull requests merge most weeks, but many recent pull requests had no comment and a stale workflow closes unconfirmed bug reports after 21 days (18 of 25). Current official npm packages, no MCP server to register (15). Six runtime dependencies, pinned actions and Scorecards, with CI failing on half of recent runs (6 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- The reasons for each of the 10 failed CI runs were not read beyond the newest, where Windows jobs failed.
- Response times on older open issues were not sampled beyond the newest 30 items.

## Weaknesses

- No MCP server, CLI or llms.txt of its own. The docs point agents to the separate chrome-devtools-mcp project
- 10 of the 20 most recent CI runs on main, 7 to 13 October 2026, concluded in failure, the newest in Windows Chrome and Firefox jobs
- Page content reaches the agent unfiltered, and the docs have no prompt-injection or untrusted-content guidance
- JavaScript and TypeScript only, with Node.js 22.12 or later required since 25.0.0
- A stale workflow marks unconfirmed bug reports after 14 days and closes them 7 days later

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Install with `npm i puppeteer`, which downloads a matching Chrome for Testing. Use `puppeteer-core` to bring your own browser
- Prefer `page.locator()` over `page.$()`. Locators wait for the element to be visible and stable before acting
- Read pages with `page.accessibility.snapshot({interestingOnly: true})` rather than full HTML to keep output short
- Catch `TimeoutError` separately from `TargetCloseError`. The first can be retried, the second needs a new page or browser
- Packages are ESM only since 25.0.0. Use `import puppeteer from 'puppeteer'` rather than `require`

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.