beast-agent@2.4.5
Ultra-fast local agent shell for Windows.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package presents real dangerous agent and remote-content capabilities, so it warrants a warning. The inspected lifecycle behavior is package-aligned and no concrete malicious installation or exfiltration chain was established.
Decision evidence
public snapshot- The runtime exposes an LLM tool that runs supplied PowerShell or Bash commands in its workspace.
- Risky tool approval is disabled by default according to the runtime configuration comment.
- The skills store fetches code-capable skill files from a remote GitHub index and writes them locally.
- The automatic postinstall repair deletes and reinstalls Electron runtime files, including use of a mirror.
- No runtime dependency on beast-agent itself was found.
- The lifecycle hook is limited to repairing the package's Electron dependency rather than changing agent configuration or the consumer project.
- Remote skills are installed through a runtime install action, not automatically during npm installation.
- The engine protects its own application directory from agent write operations.
Source & flagged code
19 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@2.4.5.
See all versions of beast-agent for other recorded verdicts.
- Review the evidence and your use of beast-agent@2.4.5 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.