@arafeymasood/rabot
An AI-powered shell with personalized LLM assistance
This report shows the evidence for @arafeymasood/rabot@2.0.2, the only known version.
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.
Decision evidence
public snapshot- 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.
- 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.
Source & flagged code
4 flaggedSource contains bidi control or invisible Unicode characters associated with Trojan Source attacks.
dist/prompts/system.jsView on unpkg · L31A package entrypoint or install-time lifecycle script reaches a source file with blocking dangerous behavior.
dist/prompts/system.jsView on unpkgFindings
Affected versions and remediation
This report applies to @arafeymasood/rabot@2.0.2.
The versions list below shows the verdict for each recorded version.
- 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.