iclavue@11.3.19
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 source excerpts support ordinary pager setup, provider authentication, and proxy configuration, without establishing an active attack. No concrete malicious behavior was verified in the reported high-risk files.
Decision evidence
public snapshot- package.json installs a pager helper after installation; source shows it chmods packaged pager-named files.
- The flagged adapter obtains Anthropic OAuth or API credentials for request headers; no unrelated recipient is established by the inspected excerpt.
- The sandbox runtime CLI parses its command-line program, and the proxy module resolves configured proxy environment values.
- No concrete credential exfiltration or malicious install-time behavior was established in the inspected source.
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@11.3.19.
See all versions of iclavue for other recorded verdicts.
- Review the evidence and your use of iclavue@11.3.19 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.