pintumcp@1.2.1
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 14d ago · by lpm-firewall-aiThe postinstall hook automatically configures the package's own MCP integration in detected AI tools, creating an agent extension lifecycle risk. The inspected behavior supports a warning, while no concrete malicious chain was established.
Decision evidence
public snapshot- package.json runs install.js from its postinstall hook.
- install.js automatically invokes the package's install command.
- The install command detects supported AI tools and configures the package's own MCP server in their settings.
- The installer creates a Python virtual environment and installs dependencies.
- The inspected setup adds a named pintumcp integration to detected tools; no credential collection or external endpoint was found in the inspected source.
Source & flagged code
8 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 unpkgpackage.json runs install.js from its postinstall hook.
package.jsonView on unpkg · L9Findings
Affected versions and remediation
This report applies to pintumcp@1.2.1.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.1 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.