pintumcp@1.2.26
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe postinstall automatically configures first-party agent notifications, including adding Claude hooks and an OpenCode plugin when those tools are present. This warrants a warning for automatic agent integration setup, but the inspected behavior does not establish malicious activity.
Decision evidence
public snapshot- The package defines a postinstall hook that runs its installer automatically.
- The installer runs the CLI install command during postinstall.
- The install command detects AI tools and configures detected integrations.
- When the Claude settings directory exists, the install command adds Claude hooks without a separate confirmation.
- When OpenCode is present, the package copies its own plugin into the global plugins directory.
- The integration changes install this package's own notification plugin and hooks, consistent with its stated agent-alert purpose.
- The package only attempts OpenCode plugin installation when its configuration directory exists.
Source & flagged code
7 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 unpkgThe package defines a postinstall hook that runs its installer automatically.
package.jsonView on unpkg · L9Findings
Affected versions and remediation
This report applies to pintumcp@1.2.26.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.26 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.