kept@0.1.0
CAUTION· install onlyPublisher claims: "An MCP server that lets an AI assistant record household spending from a sentence, receipt photo, order email or bank statement. It supplies the household's categories, people and things, notes and history along with a playbook of rules for asking questions and confirming entries before saving." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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: Caution 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
RESEND_API_KEYTURNSTILE_SECRET_KEYConfiguration, not credentials: DATABASE_OWNER_URL, KEPT_REVISION, MAIL_FROM, PUBLIC_URL, SCHEDULER_INTERVAL_MS, TRUST_PROXY, TURNSTILE_SITE_KEY- Where it talks to
- no vendor host named in the codeAlso sitemaps.org, resend.com, cloudflare.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 with a scoped credential, under the guard, and read the third-party hosts first. The code names sitemaps.org, resend.com, cloudflare.com as well as its own vendor. The guard injects RESEND_API_KEY, TURNSTILE_SECRET_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] 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 2026-11-12 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
"create-household": "tsx --env-file-if-exists=.env src/cli/create-household.ts",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."start": "node --env-file-if-exists=.env dist/server.js",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."migrate": "tsx --env-file-if-exists=.env src/cli/migrate.ts",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."dev": "tsx watch --env-file-if-exists=.env src/server.ts",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return `${[HEADER, ...rows].map((row) => row.map(csvCell).join(',')).join('\r\n')}\r\n`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.if (!value) throw new Error(`${name} is not set; see .env.example.`)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.app.get('/robots.txt', page, async (_request, reply) => reply.type('text/plain; charset=utf-8').header('cache-control', 'public, max-age=3600').send(robotsTxt(origin)))Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.return document.cookie.split('; ').find((c) => c.startsWith(`${COOKIE}=`))?.split('=')[1]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.app.get('/sitemap.xml', page, async (_request, reply) => reply.type('application/xml; charset=utf-8').header('cache-control', 'public, max-age=3600').send(sitemapXml(origin)))Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."create-client": "tsx --env-file-if-exists=.env src/cli/create-client.ts",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const userId = await createWithVerifiedEmail(deps.db, interaction.uid, { ...input, language: langOf(request) })Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.document.cookie = `${COOKIE}=${lang}; path=/; max-age=31536000; samesite=lax`Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.Cost to the agent
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.
What would make this Verified
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim np25071984: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- document.cookie access≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.