rafey-shell@1.0.4
Renamed to rabot. Install with npm install -g @arafeymasood/rabot
An AI-powered shell with personalized LLM assistance
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe package performs its advertised AI chat function, but automatically includes the local working directory in requests without disclosing that collection. This warrants a telemetry warning, not a malicious verdict.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
A user submits a query in the interactive shell.
Impact
The API receives a local filesystem path that may identify a user or project; this is warning-level telemetry, with no evidence of credential theft.
Mechanism
The client adds process.cwd() and a timestamp to the prompt, then posts the prompt and chat history to the package API.
AI rationale
The package performs its advertised AI chat function, but automatically includes the local working directory in requests without disclosing that collection. This warrants a telemetry warning, not a malicious verdict.
Evidence
dist/services/LLMService.jsapi/chat.ts
Network endpoints1
rafey-shell.vercel.app/api/chat
Decision evidence
public snapshotAI called this Suspicious at 91.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- Each user query sends a prompt and conversation history to the configured API endpoint.
- The prompt automatically includes the process working directory and timestamp; the README does not disclose this added context.
- The API handler forwards the prompt and conversation history to the configured Gemini model.
Evidence against
- The network request is part of the package’s advertised AI chat feature and follows a user query.
- No credential collection, unrelated data transfer, or hidden execution was identified in the inspected entry points and service.
- The flagged zero-width character appears in biographical text; no bidi control characters were found in the flagged source file.
Behavioral surface
EnvironmentVarsNetwork
HighEntropyStringsUrlStrings
Source & flagged code
5 flaggeddist/services/LLMService.jsView file
73contains 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/services/LLMService.jsView on unpkg · L73•Trigger-reachable chain: scripts.start -> dist/cli.js -> dist/shell/RafeyShell.js -> dist/services/LLMService.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/services/LLMService.jsView on unpkg27= await fetch(this.apiEndpoint, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
},
body:
Medium
Findings
2 Critical1 High5 Medium4 Low
CriticalTrojan Source Unicodedist/services/LLMService.js
CriticalTrigger Reachable Dangerous Capabilitydist/services/LLMService.js
HighNode Builtin Dependency Squatpackage.json
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
MediumAi Review Evidencedist/services/LLMService.js
MediumAi Review Evidencedist/services/LLMService.js
LowNon Install Lifecycle Scripts
LowScripts Present
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to rafey-shell@1.0.4.
See all versions of rafey-shell for other recorded verdicts.
- Review the evidence and your use of rafey-shell@1.0.4 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.