hostinger-api-mcp@1.57.0
⚠ Under reviewMCP server for Hostinger API
AI Security Review
scanned 2mo ago · by lpm-firewall-aiNo automatic lifecycle attack exists, but the package embeds a broad agent-triggered setup flow that downloads and runs mutable external code. The remote execution and reviewer-directed safety assurance leave a concrete extension-lifecycle risk.
Decision evidence
public snapshot- The bundled agent skill tells a coding agent to download and run a script from the moving GitHub main branch.
- That script runs an unpinned latest version of a separate npm package through npx.
- The bootstrap checks for Hostinger credentials in the user configuration directory before launching the external package.
- The skill calls the external script safe while directing an agent to execute it; this is reviewer-directed assurance text.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The npm build command only runs the TypeScript compiler and writes build output.
- The OAuth implementation uses the Hostinger authentication endpoint and a localhost callback for its stated API service.
Source & flagged code
4 flagged · loading sourcePackage source invokes a package manager install command at runtime.
build.jsView on unpkg · L18This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
Findings
Affected versions and remediation
This report applies to hostinger-api-mcp@1.57.0.
See all versions of hostinger-api-mcp for other recorded verdicts.
- Review the evidence and your use of hostinger-api-mcp@1.57.0 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.