@solongate/proxy@0.89.73
AI tool security proxy: protect any AI tool server with customizable policies, path/command constraints, rate limiting, and audit logging. No code changes required.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe source establishes a user-invoked, cross-client hook and reporting system with remote self-updates. It does not establish automatic install-time compromise or a self-dependency lifecycle chain.
Decision evidence
public snapshot- Its global installer registers command hooks for Claude Code, Codex, Antigravity, and OpenCode.
- Installed conversation hooks collect user prompts and assistant replies, then send redacted text to the vendor API with the configured bearer key.
- The guard periodically fetches a newer hook bundle and atomically replaces the installed hook.
- The installer can lock its protection files at the operating-system level.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The hook installation is reached through the package CLI and its CLI rejects agent and non-interactive invocation.
- No runtime dependency refers back to this package, and no secret harvesting outside the configured SolonGate credential was found.
Source & flagged code
26 flagged · loading sourcePackage source references child process execution.
dist/tui/index.jsView on unpkg · L143Findings
Affected versions and remediation
This report applies to @solongate/proxy@0.89.73.
See all versions of @solongate/proxy for other recorded verdicts.
- Review the evidence and your use of @solongate/proxy@0.89.73 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.