iclavue@11.4.3
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 manifest's install hook invokes a pager binary setup script, whose inspected behavior is limited to local executable permissions. Reported credential and sandbox indicators were not verified as attack behavior in the inspected source excerpts.
Decision evidence
public snapshot- package.json defines postinstall to run a package-owned pager setup script.
- The hook only locates packaged pager binaries and makes matching files executable.
- The reviewed adapter and bundled CLI sources show package and dependency implementation, with no verified credential exfiltration or attack behavior in the inspected excerpts.
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@11.4.3.
See all versions of iclavue for other recorded verdicts.
- Review the evidence and your use of iclavue@11.4.3 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.