@tenux/cli@1.0.2
Tenux — mobile-first IDE for 10x engineering
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package does not show install-time malware or credential exfiltration to an unrelated fixed endpoint. Its automatic user-scoped Claude Code MCP registration is a real, user-invoked AI-agent control-surface risk that warrants a warning.
Decision evidence
public snapshot- Starting the agent automatically adds a user-scoped Tenux MCP server to Claude Code when the Claude CLI is present.
- The registered MCP command exposes the package's workspace bridge to an AI client.
- package.json has no preinstall, install, or postinstall hook.
- The configuration change is reached from agent startup, not package installation, and networked AI providers are explicit product functionality.
Source & flagged code
12 flaggedSource appears to send environment or credential material to an external endpoint.
dist/chunk-T7K3JJWJ.jsView on unpkg · L50Findings
Affected versions and remediation
This report applies to @tenux/cli@1.0.2.
See all versions of @tenux/cli for other recorded verdicts.
- Review the evidence and your use of @tenux/cli@1.0.2 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.