webtools-mcp@r1

VERIFIED· install only

Publisher claims: "Gives coding agents web access by searching the public web, reading pages and documents as Markdown, JSON, or text, and rendering JavaScript-heavy pages in a headless browser. Deployed on Cloudflare Workers behind OAuth sign-in so only the owner can use it." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher hajikelu · publishing for 0 daysInstalls 0Last detonated 8 h ago

$npx skills add webtools-mcp

Watch Report an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.

Tested: 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: no credential variables read in the code
Where it talks to: no vendor host named in the codeAlso example.test, cloudflareaccess.com — not the publisher's domain; check what for before connecting.
What the honeypot saw: no credential files read · no network
What we could not test: use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

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

Is webtools-mcp@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-14 and scored it 91/100 (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 · 0 s · 1 scenarios · 0 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

0.0sprocessscript backend runs setup only

0.0sprocessno install scripts to re-run

Static findings

LOW

URL to a private-network addresssrc/render.test.ts:67 · URL to a private-network address — a LAN or development targetawait assert.rejects(webRenderTool(browser).execute({ url: "http://10.0.0.1/admin" }, {}), {Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.

AST07

MEDIUM

File type combined with upload action.agents/skills/update-dependencies/SKILL.md:34 · File type combined with upload action — agent may exfiltrate local data files

…needs code. If the run holds other updates, put its old version back in `package.json`, run `pnpm install`, and hold it back with anything that moves with it. If it's the run's only update, fix `src` here. Stop and ask when the fix would c…

Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.

AST07

Cost to the agent

Instructions loaded

≈2,625 tok

2 files · 27 in bundle

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

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.