spacecode@2.16.5
SpaceCode - launch cloud dev environments with AI coding agents
AI Security Review
scanned 3d ago · by lpm-firewall-aiInspected the manifest and shipped CLI, MCP, and REPL source. The scanner's credential-routing and agent-configuration signals are consistent with configurable SpaceCode authentication and project-context handling; no concrete attack behavior was established.
Decision evidence
public snapshot- package.json defines CLI entrypoints and no lifecycle scripts.
- The login flow uses a configurable auth URL that defaults to app.spacecode.app, then saves the returned key locally.
- The CLI and MCP bundle use SpaceCode service domains as their default API endpoints.
- The index scanner skips .claude directories; the REPL reads project .claude commands and skills as workspace context.
- The MCP helper starts interactive commands without a shell.
Source & flagged code
12 flagged · loading sourceManifest-reachable source sends a prompted API credential to a fixed unofficial gateway and persists the redirection.
dist/index.jsFindings
Affected versions and remediation
This report applies to spacecode@2.16.5.
See all versions of spacecode for other recorded verdicts.
- Review the evidence and your use of spacecode@2.16.5 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.