spacecode@2.16.13
SpaceCode - launch cloud dev environments with AI coding agents
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the flagged agent-related locations implement project scanning and repository context reads. The credential-related code uses a SpaceCode API key or a placeholder with SpaceCode’s own proxy, so the scanner hints do not establish an attack.
Decision evidence
public snapshot- package.json exposes the CLI and MCP entrypoints and declares no install lifecycle hook.
- The CLI’s project scan skips `.claude`; the REPL reads project command files as input to its repository context.
- The launch configuration sends a caller-provided API key directly, or uses a placeholder key with SpaceCode’s API proxy.
- The MCP entrypoint starts a stdio server.
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@2.16.13.
See all versions of spacecode for other recorded verdicts.
- Review the evidence and your use of spacecode@2.16.13 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.