vitrus@r1

VERIFIED· install only

Publisher claims: "Read-only analytics for every app you ship over MCP: users and lifecycle across all your apps, traffic, AI referrals vs crawlers, revenue, goals, funnels — every number comes back with the SQL that produced it." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher vitrus-dev · publishing for 1 daysInstalls 0Last detonated 20 h ago

$npx skills add vitrus

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: VITRUS_PASSWORDConfiguration, not credentials: DIRECTORY_PATH, MAX_PATTERN_CANDIDATES, OLLAMA_URL, VITRUS_DB, VITRUS_LLM_KEY, VITRUS_LLM_URL
Where it talks to: vitrus.dev (its own)Also chatgpt.com, perplexity.ai, google.com, ycombinator.com, signer.example, resend.com, sqlite.org — 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 with a scoped credential, under the guard, and read the third-party hosts first. The code names chatgpt.com, perplexity.ai, google.com, ycombinator.com, signer.example, resend.com, sqlite.org as well as its own vendor. The guard injects VITRUS_PASSWORD only into requests to vitrus.dev (and its subdomains) and refuses the rest.

$vet-skills run --secrets VITRUS_PASSWORD=vitrus.dev -- <the server's command>

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

Is vitrus@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 2026-11-13 and scored it 88/100 (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

HIGH

navigator.sendBeacon()packages/tracker/src/tracker.ts:154 · navigator.sendBeacon() — can silently exfiltrate datanavigator.sendBeacon(collect, new Blob([body], { type: "application/json" }));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.

AST07

HIGH

navigator.sendBeacon()packages/tracker/src/replay.ts:424 · navigator.sendBeacon() — can silently exfiltrate datanavigator.sendBeacon && navigator.sendBeacon(endpoint(false), b);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

≈2,040 tok

4 files · 80 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.