slaunt@0.1.10
Privacy-first MCP agent access auditor for Claude and Codex
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package does not automatically execute during installation, but its explicit installer registers a remote MCP server in user AI-agent configuration. That is a real, user-invoked agent capability risk rather than evidence of autonomous malware.
Decision evidence
public snapshot- An explicit CLI option installs a remote Slaunt MCP server into detected AI-client configurations.
- The installer enables that server in Codex configuration and uses a third-party HTTPS endpoint by default.
- This creates an externally controlled agent capability after a user invokes the install option.
- package.json has no install, postinstall, or preinstall lifecycle hook.
- Configuration mutation is gated by the explicit --install-slaunt command-line option.
- The installer rejects non-HTTPS remote URLs and preserves existing configurations with backups.
Source & flagged code
4 flaggedPackage metadata claims a different repository identity while copied source loads a runtime dependency bridge.
dist/explanation/local.jsView on unpkg · L311This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/explanation/local.jsView on unpkgFindings
Affected versions and remediation
This report applies to slaunt@0.1.10.
See all versions of slaunt for other recorded verdicts.
- Review the evidence and your use of slaunt@0.1.10 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.