pintumcp@1.2.34
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe automatic install-time agent setup creates a guarded, package-owned extension lifecycle risk. The inspected behavior supports a warning, not a publish block.
Decision evidence
public snapshot- package.json runs install.js from its postinstall hook, which automatically invokes the CLI install command.
- The CLI install flow configures detected AI tools and adds Claude Code hooks when its settings directory and the Python path exist.
- The Claude hook setup adds package-owned commands to multiple Claude Code events; it updates the settings file without a separate consent prompt.
- The inspected setup adds pintumcp’s own notification integration; it does not show credential collection, unrelated configuration changes, or a remote payload.
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 unpkgpackage.json runs install.js from its postinstall hook, which automatically invokes the CLI install command.
package.jsonView on unpkg · L9Findings
Affected versions and remediation
This report applies to pintumcp@1.2.34.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.34 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.