registry / AI-agent capability abuse / @livx.cc/agentx / 0.99.31

@livx.cc/agentx@0.99.31

Edge-native AI agent runtime — drives a virtual filesystem via any LLM (ai.libx.js). Same bytes run in node, browser, or edge.

AI Security Review

scanned 2mo ago · by lpm-firewall-ai

Source inspection found a real, high-impact dual-use AI-agent capability but no concrete malicious chain. Warn because LLM-directed shell execution and credential-bearing provider configuration create material runtime risk.

Static reason

No blocking static signals were detected.; previous stored version diff introduced dangerous source

Trigger

User runs agentx and authorizes or configures an agent task.

Impact

Configured agents can run commands and modify the selected workspace; provider credentials may be used with configured services.

Mechanism

LLM-directed shell, filesystem, and optional provider-network access.

AI rationale

Evidence

package.jsondist/cli.jsdist/tools.shell.js.agent/settings.jsonAGENTS.md

Network endpoints2

bodify.bod.eeregistry.npmjs.org/@livx.cc/agentx/latest

Decision evidence

public snapshot

AI called this Suspicious at 89.0% confidence as Dangerous Capability with low false-positive risk.

Evidence for warning

CLI Shell tool executes commands via /bin/sh in the selected workspace.
Runtime loads provider keys and accepts configured provider base URLs.
Optional Bodify integration sends its supplied API key to its configured service endpoint.

Evidence against

No npm preinstall, install, or postinstall hook is declared.
Update installation is reachable only through an explicit CLI update action.
Shell child processes filter common secret environment variables by default.

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShellWebSocket

Supply chain

HighEntropyStringsPossibleObfuscationUrlStrings

Manifest

WildcardDependency

scanned 5 file(s), 1.10 MB of source, external domains: 127.0.0.1, api.anthropic.com, api.firecrawl.dev, api.tavily.com, bodify.bod.ee, github.com, html.duckduckgo.com, registry.npmjs.org, www.apple.com

Source & flagged code

8 flagged

dist/index.jsView file

Lines 4860-4900javascript

4860 ["setImmediate", /\bsetImmediate\b/],

4861 ["Atomics", /\bAtomics\b/],

4862 ["SharedArrayBuffer", /\bSharedArrayBuffer\b/],

4863 ["WebAssembly", /\bWebAssembly\b/],

4864 ["Reflect", /\bReflect\b/],

4865 ["Proxy", /\bProxy\b/],

4866 ["Buffer", /\bBuffer\b/],

4867 ["while(true)", /while\s*$\s*true\s*$/],

4868 ["for(;;)", /for\s*$\s*;\s*;\s*$/],

4869 // escape sequences can smuggle a denied identifier past the substring check

4870 // (e.g. `process` parses as `process`), so forbid them outright.

4871 ["\\u escape", /\\u/],

4872 ["\\x escape", /\\x/]

4873 ];

4874 const violations = DENY.filter(([, re]) => re.test(code)).map(([name]) => name);

4875 return { ok: violations.length === 0, violations };

4876}

4877function compileSynthesizedTool(spec) {

4878 const v = validateToolCode(spec.code);

4879 if (!v.ok) throw new Error(`unsafe synthesized tool '${spec.name}': blocked tokens [${v.violations.join(", ")}]`);

4880 if (!/^[A-Za-z_]\w{0,39}$/.test(spec.name)) throw new Error(`invalid tool name '${spec.name}'`);

4881 const fn = new Function("args", "ctx", `"use strict"; return (async (args, ctx) => { ${spec.code} })(args, ctx);`);

4882 return {

Low

Eval

Package source references a known benign dynamic code generation pattern.

dist/index.jsView on unpkg · L4880

4883 name: spec.name,

4884 description: spec.description,

4885 parameters: spec.parameters ?? { type: "object", properties: {} },

4886 async run(args, ctx) {

4887 const r = await fn(args, ctx);

4888 return typeof r === "string" ? r : JSON.stringify(r ?? "");

4889 }

4890 };

4891}

4892

4893// src/FakeAIClient.ts

4894var FakeAIClient = class {

4895 seen = [];

4896 script;

4897 constructor(script) {

4898 this.script = [...script];

4899 }

4900 async chat(options) {

dist/cli.jsView file

•Manifest-reachable source captures an API credential, sends it to a fixed unofficial gateway, and persists that redirection in agent or shell configuration. dist/cli.js: await ctx.fs.writeFile(path, body); await ctx.fs.writeFile(path, current); await ctx.fs.writeFile(p, content); headers: { authorization: `Bearer ${opts.key}`, "content-type": "application/json" }, async writeFile(path, content) { for (const [p, c] of this.st.writes) await this.base.writeFile(p, c); await ctx.fs.writeFile(path, next); return join2(repoRoot, ".claude", "worktrees");

High

Credential Redirect Persistence

Manifest-reachable source sends a prompted API credential to a fixed unofficial gateway and persists the redirection.

dist/cli.jsView on unpkg

•Manifest-reachable source resolves another installed package, overwrites its runtime code, and injects package-defined remote behavior. dist/cli.js: await ctx.fs.writeFile(path, body); await ctx.fs.writeFile(path, current); await ctx.fs.writeFile(p, content); res = await doFetch(current, { signal: ctl.signal, redirect: "manual", headers: { "user-agent": "agentx (+https://github.com/Livshitz/agentx)" } }); const res = await opts.fetch("https://api.anthropic.com/v1/messages", { const tavilyEndpoint = options.endpoint ?? "https://api.tavily.com/search"; const firecrawlEndpoint = options.firecrawlEndpoint ?? "https://api.firecrawl.dev/v1/search"; const res = await doFetch("https://html.duckduckgo.com/html/?q=" + encodeURIComponent(q2), {

High

Entrypoint Foreign Package Code Overwrite

Manifest-reachable source overwrites another installed package with package-defined remote behavior.

dist/cli.jsView on unpkg

35Trigger-reachable persistence chain: manifest.bin -> dist/cli.js L35: if (content == null || typeof content === "string") return false; L36: return content.some((p) => p.type === "image_url" && (p.image_url?.url ?? "").startsWith("data:")); L37: } ... L156: try { L157: return parseImageRef(JSON.parse(content).imageRef); L158: } catch (e) { ... L295: CONFIG_FILE_RE = /(^|\/)\.(agent|claude)\/(settings(\.[\w-]+)?\.json|config\.(json|js|mjs|cjs|ts))$/i; L296: SECRET_PAIR = /((?:^|[\s,{[])(?:export\s+)?["']?[\w.\-]*(?:KEY|TOKEN|SECRET|PASSWORD|PASSWD|CREDENTIAL|PRIVATE_KEY|ACCESS_?KEY|AUTH(?:_?TOKEN)?|BEARER)[\w.\-]*["']?\s*[:=]\s*)(["']... L297: SECRET_TOKEN = /\b(sk-ant-[\w-]{12,}|sk-[A-Za-z0-9]{20,}|ghp_[A-Za-z0-9]{20,}|gho_[A-Za-z0-9]{20,}|github_pat_[\w]{20,}|xox[baprs]-[\w-]{10,}|AKIA[0-

package.jsonView file

Lines 43-83json

43 "runtime",

44 "tools",

45 "mcp",

46 "claude",

47 "sandbox"

48 ],

49 "engines": {

dist/tools.shell.jsView file

•matchType = previous_version_dangerous_delta matchedPackage = @livx.cc/agentx@0.99.26 matchedIdentity = npm:QGxpdnguY2MvYWdlbnR4:0.99.26 similarity = 0.400 summary = stored previous version shares package body but lacks this dangerous source file

High

Previous Version Dangerous Delta

This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.

dist/tools.shell.jsView on unpkg

Source & flagged code

8 flagged · loading source

dist/index.jsView file

4880if (!/^[A-Za-z_]\w{0,39}$/.test(spec.name)) throw new Error(`invalid tool name '${spec.name}'`); L4881: const fn = new Function("args", "ctx", `"use strict"; return (async (args, ctx) => { ${spec.code} })(args, ctx);`); L4882: return {

Low

Eval

Package source references a known benign dynamic code generation pattern.

dist/index.jsView on unpkg · L4880

dist/cli.jsView file

High

Credential Redirect Persistence

Manifest-reachable source sends a prompted API credential to a fixed unofficial gateway and persists the redirection.

dist/cli.jsView on unpkg

Findings

4 High7 Medium6 Low

HighCredential Redirect Persistencedist/cli.js

HighEntrypoint Foreign Package Code Overwritedist/cli.js

HighTrigger Reachable Persistencedist/cli.js

HighPrevious Version Dangerous Deltadist/tools.shell.js

MediumDynamic Requiredist/cli.js

MediumNetwork

MediumEnvironment Vars

MediumInstall Persistencedist/cli.js

MediumStructural Risk Force Deep Review

MediumRemote Tarball Dependencypackage.json

MediumWildcard Dependency

LowNon Install Lifecycle Scripts

LowScripts Present

LowEvaldist/index.js

Affected versions and remediation

This report applies to @livx.cc/agentx@0.99.31.

See all versions of @livx.cc/agentx for other recorded verdicts.

Review the evidence and your use of @livx.cc/agentx@0.99.31 before allowing it. Restrict the permissions described in this report.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.

Evidence last updated: 2026-08-25 22:41:03.419Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Affected versions and remediation

Runtime surface

Behavioral surface

Source & flagged code