pintumcp@1.2.33
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe postinstall hook automatically installs this package's own agent integrations and modifies detected agent configuration. This is a first-party agent extension lifecycle risk, but the inspected code does not establish malicious behavior.
Decision evidence
public snapshot- The package runs an install script automatically after installation.
- That script invokes the package install command, which detects installed coding tools and configures them.
- The automatic setup copies a package-owned OpenCode plugin into the user's global plugin directory.
- When Claude Code settings exist, automatic setup adds package hooks to them.
- The configuration adds this package's own named MCP entry and preserves unrelated entries in the general JSON configuration path.
- No concrete credential transfer, unrelated network recipient, or malicious payload behavior was identified in the inspected sources.
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 script automatically after installation.
package.jsonView on unpkg · L9Findings
Affected versions and remediation
This report applies to pintumcp@1.2.33.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.33 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.