pintumcp@1.2.6
Agent Alerts MCP — desktop notifications with sound for AI coding agents
AI Security Review
scanned 14d ago · by lpm-firewall-aiThe package’s automatic postinstall path mutates foreign AI-agent configurations and installs command integrations, while also establishing login startup. This meets the policy for blocking unconsented install-time AI control-surface mutation.
Decision evidence
public snapshot- package.json runs install.js from an automatic postinstall hook.
- install.js invokes the CLI install command during postinstall.
- The install command detects AI tools and configures each detected tool, then adds an OpenCode plugin and Claude Code hooks when those directories exist.
- The indicated Claude settings location is modified by adding command hooks for three events.
- The configuration helper writes the package’s MCP server entry into detected tools’ configuration.
- The install path also creates tray startup entries that run at login.
Source & flagged code
7 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgpackage.json runs install.js from an automatic postinstall hook.
package.jsonView on unpkg · L9Install-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to pintumcp@1.2.6.
See all versions of pintumcp for other recorded verdicts.
- Avoid installing pintumcp@1.2.6. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.