@adrianfathurs/plugin-agent-tracker@1.0.1
NPM package to record AI prompting and dev activity into Mandays telemetry backend.
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe postinstall hook makes an unrequested global Claude configuration change that enables tracker activity, so a warning is warranted. The inspected payload contains identifiers and counts rather than prompt content, and the source does not establish a publisher-controlled recipient or another concrete attack.
Decision evidence
public snapshot- The package postinstall automatically runs the setup script.
- The setup script targets the global Claude settings file and writes a pre-prompt tracker command to it.
- The CLI gathers the Git email and project name, then calls the tracker.
- The tracker sends agent and project identifiers, event type, prompt count, and duration to its configured endpoint.
- The endpoint defaults to localhost but can be overridden through configuration or an environment variable.
- The inspected telemetry request contains no prompt text.
- The default telemetry endpoint is localhost; the source does not establish a publisher-controlled recipient.
Source & flagged code
5 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgThe package postinstall automatically runs the setup script.
package.jsonView on unpkg · L12Findings
Affected versions and remediation
This report applies to @adrianfathurs/plugin-agent-tracker@1.0.1.
See all versions of @adrianfathurs/plugin-agent-tracker for other recorded verdicts.
- Review the evidence and your use of @adrianfathurs/plugin-agent-tracker@1.0.1 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.