@xorox-ai/agent@0.1.3
Connects a coding project to [XOROX](https://xorox.eu) — automatic engineering context for Cursor, plus on-demand access to your project's Specifications and Tasks.
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe postinstall hook makes a first-party agent integration change to Cursor project configuration without a separate setup command. Under the applicable policy, this warrants a warning for agent extension lifecycle risk; the inspected source does not establish a publish-blocking attack.
Decision evidence
public snapshot- The package runs scripts/postinstall.js automatically during npm installation.
- The install script targets the project’s .cursor/hooks.json and .cursor/mcp.json configuration files.
- It adds a before-submit hook and registers this package’s XOROX MCP server in the project configuration.
- The configuration changes register this package’s own hook and MCP server; the inspected code shows no unrelated agent configuration writes.
- No credential collection, external network request, or remote code execution was established in the inspected install path.
Source & flagged code
5 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 unpkgThe package runs scripts/postinstall.js automatically during npm installation.
package.jsonView on unpkg · L25Findings
Affected versions and remediation
This report applies to @xorox-ai/agent@0.1.3.
See all versions of @xorox-ai/agent for other recorded verdicts.
- Review the evidence and your use of @xorox-ai/agent@0.1.3 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.