langcli-com@0.1.51
Langcli - interactive AI coding assistant in the terminal
AI Security Review
scanned 14d ago · by lpm-firewall-aiThe automatic MCP setup creates a real but unresolved agent extension lifecycle risk. The inspected source does not establish unconsented broad control-surface mutation or another concrete attack, so this warrants a warning rather than a block.
Decision evidence
public snapshot- The package runs its Chrome MCP setup script automatically after installation and depends on the bridge it invokes.
- With no arguments, the setup script runs the bridge’s permission-fix, Chrome registration, and diagnostic commands.
- The inspected script delegates to the package’s declared Chrome MCP bridge dependency; it shows no credential access or remote payload execution.
- The inspected source does not establish what configuration the bridge changes or whether it reaches a foreign or broad agent control surface.
Source & flagged code
7 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgSource creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
scripts/setup-chrome-mcp.mjsView on unpkg · L11Findings
Affected versions and remediation
This report applies to langcli-com@0.1.51.
See all versions of langcli-com for other recorded verdicts.
- Review the evidence and your use of langcli-com@0.1.51 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.