pintumcp@1.2.25
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe postinstall trigger performs automatic agent configuration and plugin setup, so this merits a warning under the agent extension lifecycle policy. The reviewed code shows package-owned notification integrations and no confirmed malicious attack behavior.
Decision evidence
public snapshot- package.json runs install.js during postinstall.
- install.js automatically invokes the package CLI's install command.
- The install command detects coding tools and writes a pintumcp MCP entry to their configurations.
- If Claude Code is present, setup adds pintumcp hooks for multiple agent events.
- Setup also copies a package-owned OpenCode alerts plugin into the user's plugin directory.
- The inspected integrations configure this package's own notification server and hooks; no credential collection or network exfiltration behavior was identified in the reviewed 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 unpkgpackage.json runs install.js during postinstall.
package.jsonView on unpkg · L9Findings
Affected versions and remediation
This report applies to pintumcp@1.2.25.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.25 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.