registry / @cakagus/codeclaw / 1.4.0
@cakagus/codeclaw@1.4.0
AI agent terminal + Telegram bot untuk coding, trading, dan research — dengan skill system auto-upgrade.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe flagged gold-analysis code uses configured keys with the services they belong to and only produces Telegram output through the configured bot and chat. The manifest has no install-time hook, and the reviewed runtime behavior is consistent with the package’s stated features.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
Market analysis runs after a user requests /gold or explicitly invokes the script; the Telegram bot starts when launched.
Impact
No unauthorized credential transfer, account action, or install-time behavior was found in the reviewed paths.
Mechanism
The analysis reads service keys from config.json and sends them to their respective services; Telegram reports use the configured bot and chat.
AI rationale
The flagged gold-analysis code uses configured keys with the services they belong to and only produces Telegram output through the configured bot and chat. The manifest has no install-time hook, and the reviewed runtime behavior is consistent with the package’s stated features.
Network endpoints4
api.twelvedata.comapi.exa.aiapi.telegram.orgnfs.faireconomy.media
Decision evidence
public snapshotAI called this Clean at 94.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest has no install or lifecycle scripts; its declared scripts are user-invoked commands.
- The gold analysis reads its Twelve Data key and Telegram bot/chat settings from the package configuration.
- The gold analysis sends its Twelve Data key to Twelve Data’s own API to fetch market data.
- The Telegram bot launches gold analysis in response to a /gold command, with Telegram notification disabled in that subprocess.
- Gold analysis sends a report only when notification is enabled and uses the configured Telegram bot token and chat ID.
Evidence against
- The package uses network access and credentials for its stated AI, market-analysis, and Telegram features.
- The Telegram entry starts polling and schedules background learning when the bot is launched.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
Source & flagged code
6 flaggedbin/codeclaw.jsView file
17if (cmd === "doctor") {
L18: const { runDoctor, printDoctorReport } = await import(path.join(PKG_ROOT, "lib", "doctor.js"));
L19: const fix = argv.includes("--fix");
Medium
Dynamic Require
Package source references dynamic require/import behavior.
bin/codeclaw.jsView on unpkg · L17lib/doctor.jsView file
2import path from "node:path";
L3: import { execSync } from "node:child_process";
L4: import { CONFIG_FILE, SKILLS_DIR, SKILLS_INDEX, IS_LEGACY } from "./paths.js";
...
L7: try {
L8: return { ok: true, out: execSync(cmd, { encoding: "utf8", stdio: "pipe", timeout: 10000, shell: "/bin/bash" }).trim() };
L9: } catch (e) {
L10: return { ok: false, out: (e.stdout || "").toString().trim(), err: (e.stderr || e.message || "").toString().trim() };
L11: }
...
L13:
L14: async function tryFetch(url, opts = {}) {
L15: try {
...
L23: function isTermux() {
Medium
Install Persistence
Source writes installer persistence such as shell profile or service configuration.
lib/doctor.jsView on unpkg · L2Findings
1 Critical2 High6 Medium5 Low
CriticalHardcoded Runtime Data Exfiltrationscripts/gold-analysis.mjs#virtual:normalized:round1
HighSemantic Analysis Limitedlib/research.js#virtual:normalized:round1
HighPrevious Version Dangerous Deltatelegram.js
MediumDynamic Requirebin/codeclaw.js
MediumNetwork
MediumEnvironment Vars
MediumInstall Persistencelib/doctor.js
MediumShips Build Helperbin/tokenobral-deploy.sh
MediumStructural Risk Force Deep Review
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowNo License
Affected versions and remediation
This report applies to @cakagus/codeclaw@1.4.0.
See all versions of @cakagus/codeclaw for other recorded verdicts.
- Review the evidence and your use of @cakagus/codeclaw@1.4.0 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: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.