registry / @cakagus/codeclaw / 1.4.2
@cakagus/codeclaw@1.4.2
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 data flows use configured credentials with their corresponding services, and Telegram reporting is tied to the configured chat and user-triggered analysis. The manifest has no install lifecycle hook or other evidence of an automatic exfiltration path.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
Market analysis runs when invoked directly or after a user sends /gold; transcription follows a received voice message.
Impact
No unsolicited credential transfer, unrelated collector, or harmful automatic action was identified.
Mechanism
Configured service keys go to their corresponding APIs, and report messages go to the configured Telegram chat.
AI rationale
The flagged data flows use configured credentials with their corresponding services, and Telegram reporting is tied to the configured chat and user-triggered analysis. The manifest has no install lifecycle hook or other evidence of an automatic exfiltration path.
Network endpoints7
api.telegram.orgapi.groq.comapi.twelvedata.comapi.exa.aifred.stlouisfed.orgnfs.faireconomy.mediahtml.duckduckgo.com
Decision evidence
public snapshotAI called this Clean at 96.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest defines no install lifecycle scripts; its scripts are explicit start, Telegram, test, and badge commands.
- The gold-analysis script reads API keys and Telegram details from local config, and sends its report only to the configured chat through Telegram’s official API.
- The Telegram bot runs gold analysis in response to an explicit /gold command, with Telegram sending disabled in the child process.
- Groq credentials are used for voice transcription after a Telegram voice message is received, and the request goes to Groq’s transcription endpoint.
Evidence against
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
NoLicense
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@1.4.2.
See all versions of @cakagus/codeclaw for other recorded verdicts.
- Review the evidence and your use of @cakagus/codeclaw@1.4.2 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.