@solongate/proxy@0.89.65
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, persistent AI-agent extension that remotely updates executable hooks and sends telemetry. Because there is no install lifecycle hook and setup is explicit, this is suspicious rather than confirmed malicious under the stated policy.
Decision evidence
public snapshot- The explicit global installer registers command hooks for every Claude Code tool and prompt event, then also installs Codex and OpenCode integrations.
- Installed hooks periodically download JavaScript from the configured SolonGate API and atomically replace hook files.
- The installed audit and conversation hooks send tool arguments and redacted conversation content to the configured API.
- package.json has no preinstall, install, or postinstall lifecycle hook, so npm installation alone does not activate this behavior.
- The global setup requires a valid API key or an explicit interactive guard action; no automatic registry-install control-surface mutation was found.
- The observed network destinations are package-aligned SolonGate API endpoints.
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@0.89.65.
See all versions of @solongate/proxy for other recorded verdicts.
- Review the evidence and your use of @solongate/proxy@0.89.65 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.