@xorox-ai/agent@0.1.7
Connects a coding project to [XOROX](https://xorox.eu) — automatic engineering context for Cursor and Claude Code, plus on-demand access to your project's Specifications and Tasks.
AI Security Review
scanned 10d ago · by lpm-firewall-aiThe unprompted postinstall configures a first-party agent integration that automatically injects backend-provided context into sessions. The inspected source does not establish credential disclosure to an unrelated recipient or another concrete attack, so this warrants a warning rather than a block.
Decision evidence
public snapshot- The installer targets project-local Cursor hook and MCP configuration files.
- The npm postinstall runs the setup script, which installs the Cursor and Claude hooks and MCP entries without a consent check.
- The setup script adds its Claude hooks to the project settings.
- The Claude session hook fetches project context and tells the model to treat XOROX rules as authoritative.
- Requests use the project token with the default XOROX API host, api.xorox.eu.
- The integration uses XOROX project credentials with the package’s own default API host; no unrelated credential recipient was identified.
- No separate malicious action was established in the inspected source.
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 unpkgSource creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
Findings
Affected versions and remediation
This report applies to @xorox-ai/agent@0.1.7.
See all versions of @xorox-ai/agent for other recorded verdicts.
- Review the evidence and your use of @xorox-ai/agent@0.1.7 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.