spacecode@2.16.9
SpaceCode - launch cloud dev environments with AI coding agents
AI Security Review
scanned 3d ago · by lpm-firewall-aiDirect source inspection found no lifecycle hook, hidden credential redirect, or unconsented agent configuration change. The scanner signals did not establish malicious behavior in the inspected entrypoints and flagged locations.
Decision evidence
public snapshot- The manifest exposes CLI and MCP entrypoints; no lifecycle hook appears in the inspected manifest.
- The default backend and model proxy use SpaceCode services.
- Default model requests use a placeholder key with the SpaceCode proxy; a custom key is passed only when supplied by the caller.
- Login validates a SpaceCode API key and saves it locally.
- The CLI scan skips `.claude`; the REPL reads existing `.claude/commands` markdown files.
- The MCP entrypoint connects through standard input and output transport.
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@2.16.9.
See all versions of spacecode for other recorded verdicts.
- Review the evidence and your use of spacecode@2.16.9 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.