Skills/npm/mcp-accessibility-scanner

mcp-accessibility-scanner@5.0.1

VERIFIED· install only

Publisher claims: "A Model Context Protocol (MCP) server for performing automated accessibility scans of web pages using Playwright and Axe-core" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher justasmonkev · publishing for 580 daysInstalls 11,336Last detonated 1 h ago
$claude mcp add mcp-accessibility-scanner -- npx -y mcp-accessibility-scanner
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 78 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
PLAYWRIGHT_MCP_AUTH_TOKENPLAYWRIGHT_MCP_EXTENSION_TOKENConfiguration, not credentials: DISPLAY, PLAYWRIGHT_MCP_ALLOWED_ORIGINS, PLAYWRIGHT_MCP_ALLOWED_TOOLS, PLAYWRIGHT_MCP_ALLOWED_UPLOAD_DIRS, PLAYWRIGHT_MCP_BLOCK_SERVICE_WORKERS, PLAYWRIGHT_MCP_BLOCKED_ORIGINS, PLAYWRIGHT_MCP_BLOCKED_TOOLS, PLAYWRIGHT_MCP_BROWSER, PLAYWRIGHT_MCP_BROWSER_SESSION_TTL_MS, PLAYWRIGHT_MCP_CAPS, PLAYWRIGHT_MCP_CDP_ENDPOINT, PLAYWRIGHT_MCP_CDP_HEADERS, PLAYWRIGHT_MCP_CDP_LAUNCH_ARGS, PLAYWRIGHT_MCP_CDP_LAUNCH_COMMAND, PLAYWRIGHT_MCP_CDP_LAUNCH_CWD, PLAYWRIGHT_MCP_CDP_LAUNCH_PORT, PLAYWRIGHT_MCP_CDP_LAUNCH_STARTUP_TIMEOUT, PLAYWRIGHT_MCP_CDP_TIMEOUT, PLAYWRIGHT_MCP_CONFIG, PLAYWRIGHT_MCP_DEFAULT_TIMEOUT, PLAYWRIGHT_MCP_DEVICE, PLAYWRIGHT_MCP_EXECUTABLE_PATH, PLAYWRIGHT_MCP_FILE_PATHS, PLAYWRIGHT_MCP_HEADLESS, PLAYWRIGHT_MCP_HOST, PLAYWRIGHT_MCP_IGNORE_HTTPS_ERRORS, PLAYWRIGHT_MCP_IMAGE_RESPONSES, PLAYWRIGHT_MCP_ISOLATED, PLAYWRIGHT_MCP_MOBILE, PLAYWRIGHT_MCP_NAVIGATION_TIMEOUT, PLAYWRIGHT_MCP_NO_TAB_GROUP, PLAYWRIGHT_MCP_OUTPUT_DIR, PLAYWRIGHT_MCP_PING_TIMEOUT_MS, PLAYWRIGHT_MCP_PORT, PLAYWRIGHT_MCP_PROFILE_DIR_NAME, PLAYWRIGHT_MCP_PROXY_BYPASS, PLAYWRIGHT_MCP_PROXY_SERVER, PLAYWRIGHT_MCP_REDACT_URL_PARAMS
Where it talks to
no vendor host named in the codeAlso dequeuniversity.com — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names dequeuniversity.com as well as its own vendor. The guard injects PLAYWRIGHT_MCP_AUTH_TOKEN, PLAYWRIGHT_MCP_EXTENSION_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y mcp-accessibility-scanner

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 5.0.0

vet-skills diff mcp-accessibility-scanner 5.0.0 5.0.1

In the sandbox, this version reached for nothing 5.0.0 did not. Compared from the two recorded runs, not from source.

5.0.1 was run less far than 5.0.0 (install only vs startup only); behavior past startup is not compared.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: Node.js v22.23.5
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1: Node.js v22.23.5
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: Node.js v22.23.5
0.4sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 1: Node.js v22.23.5
0.6sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.7sprocessexited 1: Node.js v22.23.5
0.7sprocessbundled script run in the sandbox with no arguments
0.9sprocessexited 1: Node.js v22.23.5
0.9sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.0sprocessexited 1: Node.js v22.23.5
1.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.1sprocessexited 1: Node.js v22.23.5
1.1sprocess8 of 78 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.1sprocessscript backend runs setup only
1.1sprocessscript backend runs setup only
1.1sprocessno install scripts to re-run

Static findings

HIGH
Credential pass-through configurationlib/config.js:512 · Credential pass-through configuration — agent relays sensitive credentialspassword: decodeProxyCredential(url.password),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationlib/config.js:511 · Credential pass-through configuration — agent relays sensitive credentialsusername: decodeProxyCredential(url.username),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
URL with embedded credentialslib/program.js:120 · URL with embedded credentials — may be phishing or credential leaking.option('--proxy-server <proxy>', 'specify proxy server, for example "http://myproxy:3128", "http://user:password@myproxy:3128" or "socks5://myproxy:8080"')Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Credential pass-through configurationlib/config.js:517 · Credential pass-through configuration — agent relays sensitive credentialsfunction decodeProxyCredential(value) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02

Cost to the agent

Instructions loaded
≈74 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for mcp-accessibility-scanner@5.0.1 as of 37 min ago. This is the package itself, not its dependencies.