@arafeymasood/rabot@2.0.2
An AI-powered shell with personalized LLM assistance
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe package’s core function is to send user queries to its hosted AI service, but it also includes the local working directory in every request without explaining that disclosure. This is a runtime telemetry and privacy risk, not evidence of credential theft or malicious behavior.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
A user starts the interactive CLI and submits a query.
Impact
The service receives a local path that can identify the user's project or environment; the source does not show credentials or file contents being collected.
Mechanism
The query service adds the current working directory and timestamp to the prompt, then POSTs the full prompt to rafey-shell.vercel.app.
AI rationale
The package’s core function is to send user queries to its hosted AI service, but it also includes the local working directory in every request without explaining that disclosure. This is a runtime telemetry and privacy risk, not evidence of credential theft or malicious behavior.
Evidence
dist/services/LLMService.jsdist/shell/RafeyShell.jsdist/cli.js
Network endpoints1
rafey-shell.vercel.app/api/chat
Decision evidence
public snapshotAI called this Suspicious at 84.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The CLI sends requests to a fixed hosted chat endpoint unless the user sets an override.
- Each submitted prompt includes the process current working directory and a timestamp.
- The request is triggered when the user submits a query in the interactive shell.
Evidence against
- Network requests carry the user’s submitted chat prompt to the package’s chat service, which is central to the package’s stated AI assistant purpose.
- The source shows the request occurs on query submission; it does not show credential collection or automatic file access.
Behavioral surface
EnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
4 flaggeddist/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 unpkgpackage.jsonView file
•
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 Evidencedist/services/LLMService.js
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @arafeymasood/rabot@2.0.2.
See all versions of @arafeymasood/rabot for other recorded verdicts.
- Review the evidence and your use of @arafeymasood/rabot@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: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.