cyberneurova-cli@0.20.8
The CyberNeurova terminal AI coding agent
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe package is a CLI coding agent, and the reviewed provider setup routes configured credentials through the selected provider configuration. Although the bundle contains cloud metadata and command execution code, the evidence reviewed does not show automatic collection or exfiltration, or an unrelated download-and-execute path.
Decision evidence
public snapshot- The manifest exposes dist/main.mjs as the CLI and declares no install lifecycle scripts.
- Provider configuration uses each provider’s own API key environment variable; CyberNeurova’s base URL can be set through CYBERNEUROVA_BASE_URL.
- The CyberNeurova provider setup uses its configured base URL and account OAuth flow to configure the CLI’s own provider and search service.
- The bundled metadata and cloud authentication code is consistent with optional Google/AWS provider support; the reviewed excerpts do not show automatic metadata credential collection.
- The flagged download-and-run command is an installer command presented for users to invoke, not evidence of install-time execution.
- The reported command execution and output handling are consistent with a coding agent’s user-requested tools; no unrelated collector or automatic exfiltration path was established.
Source & flagged code
11 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/main.mjsView on unpkgA single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/main.mjsView on unpkg · L5Findings
Affected versions and remediation
This report applies to cyberneurova-cli@0.20.8.
See all versions of cyberneurova-cli for other recorded verdicts.
- Review the evidence and your use of cyberneurova-cli@0.20.8 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.