beast-agent@2.63.5
Ultra-fast local agent shell for Windows.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe code exposes dangerous agent command capability with approval disabled by default, so it warrants a warning. Static inspection did not establish malicious intent or a concrete install-time attack chain.
Decision evidence
public snapshot- The default agent permission set allows all tools, including shell execution.
- The command tool passes model-supplied command text to PowerShell or Bash.
- Approval prompts are disabled unless the user enables the setting, leaving non-delete actions automatically allowed.
- No runtime dependency on another beast-agent release was found.
- No direct credential-harvesting or covert exfiltration path was established in the inspected sources.
- The install hook repairs the package's Electron dependency; it does not alter AI-agent configuration.
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@2.63.5.
See all versions of beast-agent for other recorded verdicts.
- Review the evidence and your use of beast-agent@2.63.5 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.