@extenshi/mcp@0.12.0
Extenshi MCP server — bring the extension catalog (search, security, market research) and pre-publish scanning into your AI tools
AI Security Review
scanned 24d ago · by lpm-firewall-aiInspected source shows a postinstall hook that requires previously recorded telemetry consent before sending limited install metadata. The flagged distribution files show documentation links and landing-page rendering, with no concrete attack behavior identified.
Decision evidence
public snapshot- The install hook is registered as postinstall, but its network activity is gated on recorded telemetry consent and exits when consent is absent.
- When enabled, the hook sends install metadata and an anonymous identifier to its configured PostHog host; the source does not show credential collection.
- The flagged development guide defines links to Extenshi documentation and tools.
- The flagged landing-sections file renders caller-provided landing form data.
- No inspected source establishes credential theft, malicious persistence, destructive behavior, or an attack on an AI-agent control surface.
Source & flagged code
5 flaggedPackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references dynamic require/import behavior.
dist/index.jsView on unpkg · L30Findings
Affected versions and remediation
This report applies to @extenshi/mcp@0.12.0.
See all versions of @extenshi/mcp for other recorded verdicts.
- Review the evidence and your use of @extenshi/mcp@0.12.0 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.