clavue-v1@1.45.2
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 shows package-aligned diagnostic reporting with disable controls and redaction, plus user-invoked Mao subprocess behavior. The scanner’s dynamic-code and proxy findings correspond to Ajv serializer generation and sandbox HTTP proxy code, not a verified attack.
Decision evidence
public snapshot- The package exposes a CLI entry point and lists build and development scripts; no install lifecycle hook appears in the inspected manifest.
- Error reporting sends incident records to Clavue’s own service and can be disabled through settings or environment flags.
- Incident records contain client and environment metadata; error text and string context are redacted and clipped.
- The Mao subprocess command is built from a supplied prompt or explicit resume request.
- The flagged Ajv code dynamically compiles generated serializers; 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@1.45.2.
See all versions of clavue-v1 for other recorded verdicts.
- Review the evidence and your use of clavue-v1@1.45.2 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.