pintumcp@1.2.30
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe postinstall hook automatically configures this package’s own agent integrations, creating an agent extension lifecycle risk. The inspected source does not establish broader agent control or another concrete attack behavior.
Decision evidence
public snapshot- npm postinstall launches the package installer automatically.
- The installer adds Claude Code hooks when its settings directory and Python environment exist.
- The installer also copies a package-owned OpenCode plugin into the user’s global plugins directory.
- The setup is for this package’s own notification integration; no unrelated agent control behavior or credential transfer was identified in the inspected paths.
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 unpkgnpm postinstall launches the package installer automatically.
package.jsonView on unpkg · L10Findings
Affected versions and remediation
This report applies to pintumcp@1.2.30.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.30 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.