beast-agent@2.45.0
Ultra-fast local agent shell for Windows.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package is not shown to be malware, but it provides broad local command execution through an AI agent with limited approval gating. This is a real dangerous dual-use capability and merits a warning rather than a block.
Decision evidence
public snapshot- The application exposes an LLM tool that executes PowerShell commands on the user's machine.
- Its command-dispatch code evaluates the supplied command in a persistent shell.
- Non-delete commands are automatically allowed even when the application security setting is enabled.
- The install hook can remove and redownload the Electron runtime from a mirror.
- The install hook only repairs the package's Electron dependency; it does not alter AI-agent configuration or consumer project files.
- No package self-dependency or credential-harvesting and exfiltration path was found in the inspected sources.
- The command capability is an explicit feature of this local AI-agent application, not hidden install-time behavior.
Source & flagged code
27 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to beast-agent@2.45.0.
See all versions of beast-agent for other recorded verdicts.
- Review the evidence and your use of beast-agent@2.45.0 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.