clavue-v1@1.35.1
Clavue v1: lightweight four-slot (main/light/plan/review) multi-model coding CLI on the execution-first engine — overlapped cross-family review, official Clavue cloud preset (api.clavue.com) alongside any Messages-compatible provider, learned context ceil
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe inspected source supports ordinary CLI, provider, and diagnostic behavior; the incident client has reporting controls and redacts common credential formats. The scanner’s credential, evaluation, and process matches resolve to provider authentication, schema code generation, and command or proxy functionality, with no concrete attack behavior found.
Decision evidence
public snapshot- package.json exposes a CLI and its scripts contain no install lifecycle hook.
- Provider authentication uses configured credentials with the Anthropic API client’s normal endpoint default.
- Incident reports are sent only when reporting is enabled by settings or environment and use Clavue’s incident service.
- Incident text redacts common token and key formats before reporting.
- The OpenAI adapter builds authentication headers from configured API keys or tokens.
- The flagged process execution is a parameterized command runner; the flagged Ajv evaluation generates serializers from schema code, and the sandbox proxy handles HTTP CONNECT traffic.
Source & flagged code
12 flagged · loading sourcePackage source references child process execution.
dist/mao-command.jsView on unpkg · L4Findings
Affected versions and remediation
This report applies to clavue-v1@1.35.1.
See all versions of clavue-v1 for other recorded verdicts.
- Review the evidence and your use of clavue-v1@1.35.1 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.