iclavue@11.4.8
Clavue: execution-first AI coding CLI with direct repo tools, provider routing, native workflows, MCP integration, and long-session recovery
AI Security Review
scanned 13d ago · by lpm-firewall-aiThe inspected postinstall hook only adjusts permissions on bundled pager binaries. The flagged adapter and sandbox-runtime excerpts show provider authentication and configured proxy behavior, with no confirmed attack surface.
Decision evidence
public snapshot- package.json registers a postinstall hook for the pager setup script.
- The postinstall script chmods matching bundled pager binaries.
- The flagged adapter configures the Anthropic SDK to use its standard API endpoint and supplied credentials.
- The sandbox CLI describes running commands with network and filesystem restrictions.
- The parent proxy resolves proxy settings from explicit configuration or proxy environment variables.
- The required command and bundled source paths show no confirmed attack behavior in the inspected excerpts.
- The package has a postinstall lifecycle hook, which runs during installation.
Source & flagged code
14 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
dist/mao-command.jsView on unpkg · L4Findings
Affected versions and remediation
This report applies to iclavue@11.4.8.
See all versions of iclavue for other recorded verdicts.
- Review the evidence and your use of iclavue@11.4.8 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.