Skills/npm/solana

solana@0.29.3

VERIFIED· install only

Publisher claims: "A toolkit for building game economies on Solana: design, check, simulate and review shops, items, crafting, rewards, NFT staking, loot boxes and auctions as a JSON spec, with no smart contract to write. One shared program, its JS client, a CLI, and an MCP" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher xgamesfun · publishing for 23 daysInstalls 10,915Last detonated 15 min ago
$claude mcp add solana -- npx -y @xgamesfun/solana
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 59 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 0.28.31

vet-skills diff solana 0.28.31 0.29.3

In the sandbox, this version reached for nothing 0.28.31 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 81/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: Node.js v22.23.5
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: Node.js v22.23.5
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessbundled script run in the sandbox with no arguments
0.7sprocessexited 1: Node.js v22.23.5
0.7sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.9sprocessexited 1: Node.js v22.23.5
0.9sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.0sprocess8 of 59 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.0sprocessscript backend runs setup only
1.0sprocessscript backend runs setup only
1.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionjs/economy/guide.mjs:484 · File type combined with upload action — agent may exfiltrate local data files…function guideIndex() { return [ `A loot economy is one JSON spec (xsolana.json) on the shared loot program ${IDL.metadata.version}, on devnet unless it says "network": "mainnet" (real money). Nobody writes a contract: the spec is checked,…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsjs/client/cluster.js:122 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexport function clusterRpcUrl(url = globalThis.process?.env?.XSOLANA_RPC_URL || null) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagejs/connect/connect.mjs:90 · npx invocation of non-well-known package — may execute untrusted codeconst npx = ['-y', `--package=@xgamesfun/solana@${version}`, 'xsolana', 'mcp'];Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagejs/connect/connect.mjs:91 · npx invocation of non-well-known package — may execute untrusted codereturn platform === 'win32' ? { command: 'cmd', args: ['/c', 'npx', ...npx] } : { command: 'npx', args: npx };Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagejs/mcp/server.mjs:49 · npx invocation of non-well-known package — may execute untrusted code…on the person’s own computer and is signed there by a key file. In that folder: npx -y @xgamesfun/solana@${PACKAGE_VERSION} keygen ~/.config/xsolana/<name>.json makes…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandjs/approve/keyfile.mjs:222 · File permission modification command — agent changes file ownership/permissions`${target} can be read by other users of this machine (its mode is ${(info.mode & 0o777).toString(8)}). Run: chmod 600 ${target}`,Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagejs/connect/connect.mjs:84 · npx invocation of non-well-known package — may execute untrusted code* The command that starts the server: this checkout's (`local`), or the published package's. On Windows, npx is aFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionjs/economy/guide.mjs:507 · File type combined with upload action — agent may exfiltrate local data files… loot economy (* = required):` : `A loot economy is one JSON spec (xsolana.json) on the shared loot program ${IDL.metadata.version}, on devnet or on mainnet (its "network"; devnet when it names none). Nobody writes a contract: the spec is …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagejs/mcp/tools.mjs:65 · npx invocation of non-well-known package — may execute untrusted codereturn `npx -y @xgamesfun/solana@${PACKAGE_VERSION} approve${name ? ` ${name}` : ''}`;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagejs/mcp/tools.mjs:80 · npx invocation of non-well-known package — may execute untrusted codeexport const keygenCommand = keyFile => `npx -y @xgamesfun/solana@${PACKAGE_VERSION} keygen ${keyFile}`;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/xsolana.mjs:237 · npx invocation of non-well-known package — may execute untrusted code…a.com gives some), real SOL for one whose file says "network": "mainnet". Then: npx -y @xgamesfun/solana@${PACKAGE_VERSION} approve xsolana.json --keypair ${word}`, …Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/xsolana.mjs:317 · npx invocation of non-well-known package — may execute untrusted code// The package's own version first (what `npx @xgamesfun/solana@<version>` names), then the program's it is built for.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagejs/mcp/tools.mjs:758 · npx invocation of non-well-known package — may execute untrusted code…s (every step, in order, and its cost) and the commands that do it (each starts npx -y @xgamesfun/solana@${PACKAGE_VERSION} for this exact version: give them as they …Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagejs/mcp/server.mjs:2 · npx invocation of non-well-known package — may execute untrusted code// opencode, Cline). It has no dependencies, so `npx -y --package=@xgamesfun/solana@<version> xsolana mcp` starts in theFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsjs/client/cluster.js:35 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst fromEnv = globalThis.process?.env?.XSOLANA_CLUSTER?.trim() || null;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagejs/mcp/server.mjs:106 · npx invocation of non-well-known package — may execute untrusted codetext: `${name} works on the person’s own files, so it runs only in the local server (npx -y --package=@xgamesfun/solana@${PACKAGE_VERSION} xsolana mcp).`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionjs/mcp/server.mjs:49 · File type combined with upload action — agent may exfiltrate local data files… as "spec" to every tool.', `To go live, the spec goes in a file named xsolana.json on the person’s own computer and is signed there by a key file. In that folder: npx -y @xgamesfun/solana@${PACKAGE_VERSION} keygen ~/.config/xsolana/<name>…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 packagejs/mcp/tools.mjs:40 · npx invocation of non-well-known package — may execute untrusted code/** This package's exact version: every command the tools hand a person names it, so npx runs this very release. */Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈90 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

Not checked against OSV yet; the weekly check has not reached this version.