pintumcp@1.2.11
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe postinstall automatically configures package-owned AI tool integrations and adds event hooks, establishing a guarded agent extension lifecycle risk. The inspected behavior supports a warning, not a confirmed attack.
Decision evidence
public snapshot- package.json runs install.js during postinstall.
- The install command adds Claude Code hooks and copies the package’s OpenCode plugin into user configuration.
- The hooks register package-owned notification commands for five Claude Code events.
- The setup targets named integrations and invokes the package’s own hook and plugin files.
- The inspected setup shows no credential forwarding or unrelated remote payload execution.
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 during postinstall.
package.jsonView on unpkg · L9Findings
Affected versions and remediation
This report applies to pintumcp@1.2.11.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.11 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.