registry / Telemetry / rafey-shell

rafey-shell

Renamed to rabot. Install with npm install -g @arafeymasood/rabot

An AI-powered shell with personalized LLM assistance

This report shows the evidence for rafey-shell@2.0.2. 0 of 6 known versions are blocked or flagged. See all versions.

AI Security Review

scanned 2d ago · by lpm-firewall-ai

The CLI sends the current working directory to the package's API with each chat prompt, without disclosing that collection. This is suspicious runtime telemetry; the reviewed source does not show credential theft or other malicious behavior.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

A user runs the CLI and submits a chat message.

Impact

The package service and its model provider receive the user's local working directory alongside chat data.

Mechanism

The client adds process.cwd() to the prompt and posts it to the package API, which sends it to Gemini.

AI rationale

Evidence

dist/cli.jsdist/services/LLMService.jsapi/chat.tsREADME.md

Network endpoints1

rafey-shell.vercel.app

Decision evidence

public snapshot

AI called this Suspicious at 91.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The CLI is the package entry point and starts the interactive shell by default.
The client sends its assembled prompt to rafey-shell.vercel.app without an explicit consent step.
The assembled prompt includes the current working directory and user query.
The package API forwards the prompt to Google’s Gemini service.
The README describes chatting with an AI assistant but does not disclose sending the working directory.

Evidence against

The prompt contains user queries and conversation history for the advertised chat feature.
I found no code that collects or transmits credentials, or performs unrelated account actions.
The prepare script only runs the TypeScript build.

Behavioral surface

Source

EnvironmentVarsFilesystemNetwork

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 6 file(s), 21.9 KB of source, external domains: rafey-shell.vercel.app

Source & flagged code

4 flagged

dist/prompts/system.jsView file

31contains invisible/control Unicode U+200B (zero width space) - Research Scientist at Guy's and St Thomas'<U+200B> NHS Foundation Trust (July 2018 - October 2018): Worked closely with senior physicians @ Guy's Hospital to develop a web application to detect irregularities in MRI scans. The tool analyz

Critical

Trojan Source Unicode

Source contains bidi control or invisible Unicode characters associated with Trojan Source attacks.

dist/prompts/system.jsView on unpkg · L31

•Trigger-reachable chain: scripts.start -> dist/cli.js -> dist/shell/RafeyShell.js -> dist/services/LLMService.js -> dist/prompts/system.js Reachable file contains a blocking source-risk pattern.

Critical

Trigger Reachable Dangerous Capability

A package entrypoint or install-time lifecycle script reaches a source file with blocking dangerous behavior.

dist/prompts/system.jsView on unpkg

package.jsonView file

•Runtime dependency names matching Node built-ins: readline

Findings

2 Critical1 High4 Medium5 Low

CriticalTrojan Source Unicodedist/prompts/system.js

CriticalTrigger Reachable Dangerous Capabilitydist/prompts/system.js

HighNode Builtin Dependency Squatpackage.json

MediumNetwork

MediumEnvironment Vars

MediumStructural Risk Force Deep Review

MediumAi Review Evidencepackage.json

LowNon Install Lifecycle Scripts

LowScripts Present

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

Affected versions and remediation

This report applies to rafey-shell@2.0.2.

The versions list below shows the verdict for each recorded version.

Review the evidence and your use of rafey-shell@2.0.2 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: 2026-11-02 22:24:40.346Z (UTC).

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

Versions

6 known versions

2.0.2latestshownSuspiciousTelemetryWarnPublishedOct 14, 2026, 9:33 PM 2.0.1SuspiciousTelemetryWarnPublishedOct 14, 2026, 9:15 PM 1.0.6SuspiciousTelemetryWarnPublishedOct 14, 2026, 9:01 PM 1.0.5SuspiciousTelemetryWarnPublishedOct 13, 2026, 10:46 AM

registry / Telemetry / rafey-shell

rafey-shell

Renamed to rabot. Install with npm install -g @arafeymasood/rabot

An AI-powered shell with personalized LLM assistance

This report shows the evidence for rafey-shell@2.0.2. 0 of 6 known versions are blocked or flagged. See all versions.

AI Security Review

scanned 2d ago · by lpm-firewall-ai

Static reason

High-risk behavior combination matched malicious policy.

Trigger

A user runs the CLI and submits a chat message.

Impact

The package service and its model provider receive the user's local working directory alongside chat data.

Mechanism

The client adds process.cwd() to the prompt and posts it to the package API, which sends it to Gemini.

AI rationale

Evidence

dist/cli.jsdist/services/LLMService.jsapi/chat.tsREADME.md

Network endpoints1

rafey-shell.vercel.app

Decision evidence

public snapshot

AI called this Suspicious at 91.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

The CLI is the package entry point and starts the interactive shell by default.
The client sends its assembled prompt to rafey-shell.vercel.app without an explicit consent step.
The assembled prompt includes the current working directory and user query.
The package API forwards the prompt to Google’s Gemini service.
The README describes chatting with an AI assistant but does not disclose sending the working directory.

Evidence against

The prompt contains user queries and conversation history for the advertised chat feature.
I found no code that collects or transmits credentials, or performs unrelated account actions.
The prepare script only runs the TypeScript build.

Behavioral surface

Source

EnvironmentVarsFilesystemNetwork

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 6 file(s), 21.9 KB of source, external domains: rafey-shell.vercel.app

Source & flagged code

4 flagged

dist/prompts/system.jsView file

Critical

Trojan Source Unicode

Source contains bidi control or invisible Unicode characters associated with Trojan Source attacks.

dist/prompts/system.jsView on unpkg · L31

•Trigger-reachable chain: scripts.start -> dist/cli.js -> dist/shell/RafeyShell.js -> dist/services/LLMService.js -> dist/prompts/system.js Reachable file contains a blocking source-risk pattern.

Critical

Trigger Reachable Dangerous Capability

A package entrypoint or install-time lifecycle script reaches a source file with blocking dangerous behavior.

dist/prompts/system.jsView on unpkg

package.jsonView file

•Runtime dependency names matching Node built-ins: readline

Findings

2 Critical1 High4 Medium5 Low

CriticalTrojan Source Unicodedist/prompts/system.js

CriticalTrigger Reachable Dangerous Capabilitydist/prompts/system.js

HighNode Builtin Dependency Squatpackage.json

MediumNetwork

MediumEnvironment Vars

MediumStructural Risk Force Deep Review

MediumAi Review Evidencepackage.json

LowNon Install Lifecycle Scripts

LowScripts Present

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

Affected versions and remediation

This report applies to rafey-shell@2.0.2.

The versions list below shows the verdict for each recorded version.

Review the evidence and your use of rafey-shell@2.0.2 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: 2026-11-02 22:24:40.346Z (UTC).

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

Versions

6 known versions