@solongate/proxy@0.89.84
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 2mo ago · by lpm-firewall-aiThis is a vendor-aligned but powerful AI-agent extension that collects conversation telemetry and self-updates after explicit setup. It warrants a warning, not a publish block, because no npm install lifecycle hook or concrete malicious action was found.
Decision evidence
public snapshot- Explicit global setup registers command hooks for Claude Code, Codex, Antigravity, and OpenCode.
- The Codex registration runs guard, audit, and conversation scripts for tool and prompt events.
- The conversation hook sends redacted prompt or conversation text to the vendor API using the configured API key.
- Installed guard hooks download and atomically replace hook files from the vendor API.
- package.json contains no npm preinstall, install, or postinstall lifecycle hook.
- The agent configuration changes occur in explicit global-install code and the package uses its own SolonGate API domain.
Source & flagged code
27 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@0.89.84.
See all versions of @solongate/proxy for other recorded verdicts.
- Review the evidence and your use of @solongate/proxy@0.89.84 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.