spacecode@2.16.4
SpaceCode - launch cloud dev environments with AI coding agents
AI Security Review
scanned 3d ago · by lpm-firewall-aiSource inspection supports normal CLI, MCP, and repository integration behavior. The scanner’s similarity and credential-redirection labels were not supported by inspected attack behavior.
Decision evidence
public snapshot- package.json exposes CLI and MCP entrypoints for SpaceCode.
- The flagged index.js location skips `.claude` while scanning project directories.
- The flagged REPL location reads project Claude command files; repo commands are loaded only for trusted or session-trusted repos.
- The runtime uses a placeholder API key in proxy mode and forwards a custom API key only when supplied by the caller.
- The MCP entrypoint starts a standard input/output server.
- The inspected source did not establish unauthorized credential transfer, unconsented agent configuration changes, or other concrete attack behavior.
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@2.16.4.
See all versions of spacecode for other recorded verdicts.
- Review the evidence and your use of spacecode@2.16.4 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.