pintumcp@1.2.18
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 9d ago · by lpm-firewall-aiThe lifecycle hook automatically configures package-owned agent integrations without a separate consent step. This is an agent extension lifecycle risk; the inspected sources do not establish a concrete malicious attack.
Decision evidence
public snapshot- package.json runs install.js as a postinstall hook.
- install.js launches the CLI install command during postinstall.
- The CLI defaults to install and configures detected tools, then installs its OpenCode plugin and Claude Code hooks when their directories exist.
- The specified Claude settings location calls addHooks; the hook helper registers package-owned commands for five Claude Code events.
- The Claude hook uses prompt text, limited to 80 characters, in its status message.
- The integrations configure this package’s own MCP entry and package-owned plugin or hooks; inspected code did not establish a write to unrelated agent settings or a remote prompt collector.
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 as a postinstall hook.
package.jsonView on unpkg · L9Findings
Affected versions and remediation
This report applies to pintumcp@1.2.18.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.18 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.