Skills/Glama/kaspa-mcp

kaspa-mcp@0.2.0

CAUTION· install only

Publisher claims: "Enables AI assistants to brainstorm Kaspa ideas, compile and deploy Solidity smart contracts on Kasplex and Igra networks, and perform L1 reads and contract interactions through MCP tools." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher mikeykaspa · publishing for 3 daysInstalls 0Last detonated 3d ago

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
KASPA_PRIVATE_KEYKASPA_SPENDING_PRIVATE_KEYMCP_AUTH_TOKENConfiguration, not credentials: COMPILE_RATE_LIMITER, KASPA_ADDRESS, KASPA_L1_BROWSER_BUILD, KASPA_L1_MAINNET_WRITES, KASPA_MAINNET_RPC_URL, KASPA_MCP_BUILD_TIME, KASPA_MCP_GIT_SHA, KASPA_MCP_VERSION, KASPA_OWN_NODE_WRPC, KASPA_REST_URLS, KASPA_RPC_URL, KASPA_SPENDING_MAIN_ADDRESS, KASPA_SPENDING_MAINNET, KASPA_SPENDING_MAX_KAS, KASPA_SPENDING_MAX_TX_KAS, KASPA_SPENDING_REGISTRY_JSON, KASPA_SPENDING_REGISTRY_PATH, KASPA_SPENDING_WALLET_PATH, LOCAL_ANVIL_RPC, MAX_CACHE_KEY_CHARS, MCP_PUBLIC, MCP_URL, NO_POPUP_PATH_PLAIN, ONLY, ORPHAN_WAIT_MS, RATE_LIMIT_COMPILE, RATE_LIMIT_COMPILE_PERIOD_SEC, RATE_LIMIT_ENABLED, RATE_LIMIT_IP_CEILING, RATE_LIMIT_IP_CEILING_PERIOD_SEC, RATE_LIMIT_REQUESTS, RATE_LIMIT_REQUESTS_PERIOD_SEC, REQUEST_RATE_LIMITER, SELFHOST_BASE, SIGN_BASE_URL, SIGN_PUBLIC_BASE_URL, SIGN_SESSIONS
Where it talks to
kaspa.stream, kaspa.org, kaspanet.io, kaspafoundation.org, kaspafinance.io, kaspa-mcp.rate (its own)Also workers.dev, igralabs.com, kasplextest.xyz, kasplex.org, soliditylang.org, kasware.xyz, kasstacker.org, getfoundry.sh, cloudflare.com, kaspa.blue — 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, igralabs.com, kasplextest.xyz, kasplex.org, soliditylang.org, kasware.xyz, kasstacker.org, getfoundry.sh, cloudflare.com, kaspa.blue as well as its own vendor. The guard injects KASPA_PRIVATE_KEY, KASPA_SPENDING_PRIVATE_KEY, MCP_AUTH_TOKEN only into requests to kaspa.stream (and its subdomains) and refuses the rest.

$vet-skills run --secrets KASPA_PRIVATE_KEY=kaspa.stream,KASPA_SPENDING_PRIVATE_KEY=kaspa.stream,MCP_AUTH_TOKEN=kaspa.stream -- <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 2026-11-11 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Auto-update or dynamic fetch configuration; Auto-update or dynamic fetch configuration. 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
URL with suspicious TLDscripts/e2e-aon-tn10.mjs:24 · URL with suspicious TLD — commonly used for phishing/malwareconst EX = (txid) => `https://tn10.kaspa.stream/transactions/${txid}`;Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Auto-update or dynamic fetch configurationsrc/server.ts:2393 · Auto-update or dynamic fetch configuration — agent may load new code at runtime? { step: "self_host", args: { step: "update" }, neverAutoUpdate: true }Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/e2e-aon-share-claim.mjs:160 · File type combined with upload action — agent may exfiltrate local data filesconsole.log("l1Build p2shInputs", built.inputCount, "total", built.totalSompi);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
URL with suspicious TLDscripts/e2e-aon-share-claim.mjs:21 · URL with suspicious TLD — commonly used for phishing/malwareconst EX = (txid) => `https://tn10.kaspa.stream/transactions/${txid}`;Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDscripts/e2e-sign-browser.mjs:289 · URL with suspicious TLD — commonly used for phishing/malwarefundExplorer: `https://tn10.kaspa.stream/transactions/${fundRes.txid}`,Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDscripts/e2e-sign-browser.mjs:291 · URL with suspicious TLD — commonly used for phishing/malwarespendExplorer: `https://tn10.kaspa.stream/transactions/${spendRes.txid}`,Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Auto-update or dynamic fetch configurationsrc/self-host.ts:333 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeneverAutoUpdate: true,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with suspicious TLDscripts/e2e-l1-tn10.mjs:199 · URL with suspicious TLD — commonly used for phishing/malwarespendExplorer: `https://tn10.kaspa.stream/transactions/${spendTxid}`,Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDscripts/e2e-l1-tn10.mjs:197 · URL with suspicious TLD — commonly used for phishing/malwarefundExplorer: `https://tn10.kaspa.stream/transactions/${fundTxid}`,Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Auto-update or dynamic fetch configurationsrc/version.ts:150 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeupdate: { tool: "self_host"; args: { step: "update" }; neverAutoUpdate: true };Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with suspicious TLDscripts/e2e-l1-thorough.mjs:28 · URL with suspicious TLD — commonly used for phishing/malwareconst EX = (id) => `https://tn10.kaspa.stream/transactions/${id}`;Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Auto-update or dynamic fetch configurationsrc/version.ts:164 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeupdate: { tool: "self_host", args: { step: "update" }, neverAutoUpdate: true },Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/selfhost-setup.mjs:10 · npx invocation of non-well-known package — may execute untrusted code* npx wrangler login # onceFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/spending-wallet.ts:452 · npx invocation of non-well-known package — may execute untrusted codewranglerHint: `printf '%s' '<key>' | npx wrangler secret put ${SPENDING_ENV_KEY} -c wrangler.selfhost.toml`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/rate-limit.ts:40 · npx invocation of non-well-known package — may execute untrusted code"Rate limit exceeded on the shared demo. Self-host for heavy use: one-click Deploy to Cloudflare in the README (own free 100k req/day), or run locally with npm start / npx (no shared limits).";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with suspicious TLDsrc/l1/confirm.ts:28 · URL with suspicious TLD — commonly used for phishing/malware: `https://tn10.kaspa.stream/transactions/${txid}`;Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDsrc/networks.ts:109 · URL with suspicious TLD — commonly used for phishing/malwareexplorerUrl: "https://tn10.kaspa.stream",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File type combined with upload actionsrc/sign/page.ts:139 · File type combined with upload action — agent may exfiltrate local data files…\" + encodeURIComponent(txid))\n .then(function (r) {\n return r.json();\n })\n .then(function (body) {\n var exp = body.url || String(txid);\n showSuccess(txid, exp);\n });\n });\n }\n\n\n function $(id) { return document.getElementById(i…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/self-host.ts:254 · npx invocation of non-well-known package — may execute untrusted codeprintf '%s' '0xYOUR_KEY' | npx wrangler secret put KASPA_SPENDING_PRIVATE_KEY -c wrangler.selfhost.tomlFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/spending-wallet.ts:448 · npx invocation of non-well-known package — may execute untrusted code` printf '%s' '<paste-key-here>' | npx wrangler secret put ${SPENDING_ENV_KEY} -c wrangler.selfhost.toml\n` +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/self-host.ts:169 · npx invocation of non-well-known package — may execute untrusted code# or: npx wrangler deploy -c wrangler.selfhost.tomlFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with suspicious TLDsrc/sign/page.ts:139 · URL with suspicious TLD — commonly used for phishing/malware…\n } else if (dest) {\n html +=\n '<a class=\"secondary\" href=\"https://tn10.kaspa.stream/addresses/' +\n encodeURIComponent(dest) +\n '\" target=\"_blank\…Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/self-host.ts:329 · npx invocation of non-well-known package — may execute untrusted codenpx wrangler deploy -c wrangler.selfhost.tomlFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with suspicious TLDsrc/sign/summary.ts:147 · URL with suspicious TLD — commonly used for phishing/malwarereturn `https://kaspa.stream/transactions/${txid}`;Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDsrc/campaign-page.ts:107 · URL with suspicious TLD — commonly used for phishing/malwarereturn netOf(networkId) === "mainnet" ? "https://kaspa.stream" : "https://tn10.kaspa.stream";Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/self-host.ts:167 · npx invocation of non-well-known package — may execute untrusted codenpx wrangler loginFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/spending-wallet.ts:456 · npx invocation of non-well-known package — may execute untrusted code`2. In your kaspa-mcp folder (same -c file you deployed): printf '%s' '0x…' | npx wrangler secret put ${SPENDING_ENV_KEY} -c wrangler.selfhost.toml`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with suspicious TLDsrc/sign/summary.ts:144 · URL with suspicious TLD — commonly used for phishing/malwarereturn `https://tn10.kaspa.stream/transactions/${txid}`;Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
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

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim mikeykaspa: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  3. URL with suspicious TLD≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  4. 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.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim mikeykaspaPropose a patch to the maintainer