pintumcp@1.2.35
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 8d ago · by lpm-firewall-aiStatic source confirms automatic first-party agent integration and global settings changes during npm installation. This warrants a warning for agent extension lifecycle risk, but the inspected behavior does not establish a concrete attack supporting a publish block.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
Installing the package with npm runs its post-install setup.
Impact
The hooks summarize some agent activity, including shortened prompt text, and store status information in the user's local application data for display.
Mechanism
The setup command detects installed tools, adds MCP entries, and registers Claude Code hooks for prompt, tool, and session events.
AI rationale
Static source confirms automatic first-party agent integration and global settings changes during npm installation. This warrants a warning for agent extension lifecycle risk, but the inspected behavior does not establish a concrete attack supporting a publish block.
Evidence
package.jsoninstall.jsbin/pintumcp.jslib/hooks.jspython/hook.pypython/status.py
Decision evidence
public snapshotAI called this Suspicious at 92.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest runs a post-install script that starts setup automatically.
- The post-install script launches the CLI with its install action.
- The installer detects existing AI tools and configures their MCP entries before setting up alerts.
- When Claude Code's settings directory exists, the install path adds the package hook to its global settings without a confirmation prompt.
- The hook writer adds package-owned commands to Claude lifecycle events in the settings file.
- The hook shortens prompt text and sends status summaries to per-user local storage.
Evidence against
- The hooks provide the package's notification integration and store status locally; the reviewed source does not establish a separate attack chain.
Behavioral surface
ChildProcessEnvironmentVarsFilesystemShell
HighEntropyStrings
Source & flagged code
7 flagged · loading sourcepackage.jsonView file
•scripts.postinstall = node install.js
High
Install Time Lifecycle Scripts
Package defines install-time lifecycle scripts.
package.jsonView on unpkg•scripts.postinstall = node install.js
Medium
Ambiguous Install Lifecycle Script
Install-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkg10"postinstall": "node install.js"
},
"keywords": [
"mcp",
"notificati
Medium
Ai Review Evidence
The manifest runs a post-install script that starts setup automatically.
package.jsonView on unpkg · L10python/tray_cross.pyView file
•
Findings
2 High7 Medium3 Low
HighInstall Time Lifecycle Scriptspackage.json
HighPrevious Version Dangerous Deltabin/pintumcp.js
MediumAmbiguous Install Lifecycle Scriptpackage.json
MediumEnvironment Vars
MediumShips Build Helperpython/tray_cross.py
MediumStructural Risk Force Deep Review
MediumAi Review Evidencepackage.json
MediumAi Review Evidenceinstall.js
MediumAi Review Evidencebin/pintumcp.js
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
Affected versions and remediation
This report applies to pintumcp@1.2.35.
See all versions of pintumcp for other recorded verdicts.
- Review the evidence and your use of pintumcp@1.2.35 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.