pintumcp@1.2.12
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe postinstall hook automatically modifies detected agent configuration and may add Claude Code hooks, creating a guarded agent integration lifecycle risk. The inspected behavior is package-owned setup, with no evidence of a concrete attack that warrants blocking publication.
Decision evidence
public snapshot- The package runs an install.js script during postinstall, which launches the CLI install command.
- The install command detects available coding tools and configures the package for detected tools.
- When a Claude Code settings directory exists, setup adds pintumcp hooks for several events.
- The detector targets multiple agent and editor configurations, including Claude, Codex, OpenCode, and VS Code.
- The configuration entries and hooks point to pintumcp’s own server and hook files.
- Setup is limited to detected tools or existing agent configuration locations; inspected code showed no credential collection or network transmission.
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 runs an install.js script during postinstall, which launches the CLI install command.
package.jsonView on unpkg · L9Findings
Affected versions and remediation
This report applies to pintumcp@1.2.12.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.12 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.