spacecode@2.16.6
SpaceCode - launch cloud dev environments with AI coding agents
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe manifest exposes CLI entry points and contains no lifecycle hook. Inspected credential handling targets SpaceCode’s service by default, while the flagged agent-related code reads project files without changing agent configuration.
Decision evidence
public snapshot- package.json exposes the SpaceCode CLI and MCP binaries from dist.
- Authentication defaults to SpaceCode’s backend and app; saved-session requests use the configured API URL.
- The API URL is saved through a CLI config command, and the client sends the saved token to that URL.
- The flagged agent-related code reads project files under .claude; it does not modify agent settings.
- The MCP server exposes remote_exec as a tool that dispatches a supplied repository and prompt to a remote sandbox.
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@2.16.6.
See all versions of spacecode for other recorded verdicts.
- Review the evidence and your use of spacecode@2.16.6 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.