Skills/Glama/tabularium-mcp

tabularium-mcp@0.1.0

CAUTION· install only

Publisher claims: "Enables AI agents to store and retrieve persistent memory across sessions and machines, and to pay any x402 API while keeping a signed, offline-verifiable ledger of purchases and spending." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher sqlazy · publishing for 1 daysInstalls 0Last detonated 18 h ago
What would fix thisWatchDispute verdict

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
CDP_API_KEY_IDCDP_API_KEY_SECRETROBOTS_TOKENSIGNING_KEY_PKCS8SIGNING_PUBKEY_HEXTABULARIUM_PRIVATE_KEYConfiguration, not credentials: AYB_RPC, EXCLUDE_WALLETS, FACILITATOR_URL, GITHUB_ACTIONS, MCP_PATH, NETWORK, PAY_TO, PAYER_FILE, STATS, TABULARIUM_MAX_SPEND_USD, TABULARIUM_PAY_MAX_USD, TABULARIUM_PAY_NETWORKS, TABULARIUM_PUBKEY, TABULARIUM_RPC_URL, TABULARIUM_STATE_DIR, TABULARIUM_TEST, TABULARIUM_URL, TESTNET_PAYER_KEY, WORKSPACE
Where it talks to
no vendor host named in the codeAlso workers.dev, publicnode.com, coinbase.com, evil.example, httpbin.org, google.com, irs.gov, fsu.edu, x402.org, githubusercontent.com, x.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 workers.dev, publicnode.com, coinbase.com, evil.example, httpbin.org, google.com, irs.gov, fsu.edu, x402.org, githubusercontent.com, x.com as well as its own vendor. The guard injects CDP_API_KEY_ID, CDP_API_KEY_SECRET, ROBOTS_TOKEN, SIGNING_KEY_PKCS8, SIGNING_PUBKEY_HEX, TABULARIUM_PRIVATE_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$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 [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 2026-11-13 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: URL to the cloud instance metadata address; 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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known package.github/workflows/test.yml:120 · npx invocation of non-well-known package — may execute untrusted coderun: node smoke.mjs --npx tabularium-mcp@${{ inputs.mcp_npx }} http://127.0.0.1:8788Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with embedded credentialstest/snapshot.test.ts:17 · URL with embedded credentials — may be phishing or credential leaking["https://user:[email protected]/", "url_credentials_not_allowed"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actionscripts/gen-key.mjs:16 · File type combined with upload action — agent may exfiltrate local data filesconsole.log("\nSecret (pipe into: npx wrangler secret put SIGNING_KEY_PKCS8):\n " + pkcs8);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/llms.ts:79 · npx invocation of non-well-known package — may execute untrusted codeclaude mcp add tabularium --env TABULARIUM_PRIVATE_KEY=0x... -- npx -y tabularium-mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Hex-encoded URLtest/snapshot.test.ts:21 · Hex-encoded URL — attempt to bypass URL filtering["http://0x7f.1/", "ip_address_not_allowed"],Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/e2e.mjs:2 · npx invocation of non-well-known package — may execute untrusted code// npx wrangler dev -c wrangler.dev.jsonc --port 8787 (in another shell)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL to the cloud instance metadata addresstest/snapshot.test.ts:23 · URL to the cloud instance metadata address — reads the VM's credentials["http://169.254.169.254/latest/meta-data", "ip_address_not_allowed"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actionscripts/gen-key.mjs:15 · File type combined with upload action — agent may exfiltrate local data filesconsole.log("Public (put in wrangler.jsonc vars.SIGNING_PUBKEY_HEX):\n " + pubHex);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/release-mcp.mjs:46 · npx invocation of non-well-known package — may execute untrusted coderun("npx vitest run", ".");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
URL to the cloud instance metadata addressscripts/e2e.mjs:281 · URL to the cloud instance metadata address — reads the VM's credentials["cloud metadata", { url: "http://169.254.169.254/latest/meta-data" }, 400, "ip_address_not_allowed"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packagetest/mcp-shrinkwrap.test.mjs:1 · npx invocation of non-well-known package — may execute untrusted code// tabularium-mcp ships npm-shrinkwrap.json so `npx tabularium-mcp` installs exactly the dependency tree we tested.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagemcp/smoke.mjs:20 · npx invocation of non-well-known package — may execute untrusted code? { command: "npx", args: ["-y", npxSpec], cwd: tmpdir() } // empty-ish dir, so npx fetches from the registryFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/gen-key.mjs:16 · npx invocation of non-well-known package — may execute untrusted codeconsole.log("\nSecret (pipe into: npx wrangler secret put SIGNING_KEY_PKCS8):\n " + pkcs8);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagemcp/smoke.mjs:12 · npx invocation of non-well-known package — may execute untrusted code// --npx <spec> tests the published package (e.g. --npx [email protected]) instead of the local server.mjs.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/release-mcp.mjs:33 · npx invocation of non-well-known package — may execute untrusted codeconst lockPath = "mcp/npm-shrinkwrap.json"; // shipped in the package, so npx installs exactly these versionsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.github/workflows/test.yml:71 · npx invocation of non-well-known package — may execute untrusted codenpx wrangler dev -c wrangler.dev.jsonc --port 8787 > wrangler.log 2>&1 &Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languageSECURITY.md:42 · Authorization escalation language · informational: not an instruction file- **Signing key.** Held only as a Cloudflare secret; anyone with Worker-admin access could sign heads. RotationFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsscripts/e2e.mjs:282 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files["a non-http scheme", { url: "file:///etc/passwd" }, 400, "url_scheme_not_allowed"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstest/snapshot.test.ts:15 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files["file:///etc/passwd", "url_scheme_not_allowed"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/services/snapshot-core.ts:4 · File type combined with upload action — agent may exfiltrate local data files/** Our robots.txt product token and the User-Agent the fetcher sends. */Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known package.github/workflows/test.yml:106 · npx invocation of non-well-known package — may execute untrusted codenpx wrangler dev -c wrangler.ci.jsonc --port 8788 > wrangler.log 2>&1 &Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL to the cloud instance metadata addresstest/snapshot.test.ts:130 · URL to the cloud instance metadata address — reads the VM's credentials…host_not_allowed"], ["http://127.0.0.1/", "redirect_ip_address_not_allowed"], ["http://169.254.169.254/latest", "redirect_ip_address_not_allowed"], ["http://db.internal/", "redirect_…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07

Cost to the agent

Instructions loaded
≈34 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

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

What would make this Verified

7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim sqlazy: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  4. URL with embedded credentials≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. 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.
  6. Hex-encoded URL≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim sqlazyPropose a patch to the maintainer