@solongate/proxy@0.89.18
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 user-invoked, first-party AI-agent extension with remote hook updates and cloud telemetry, so it warrants a warning. The inspected manifest has no lifecycle scripts, and no concrete unconsented install-time attack or unrelated exfiltration chain was found.
Decision evidence
public snapshot- The explicit global installer writes and registers hooks for Claude Code, Codex, Antigravity, and OpenCode.
- Installed guard hooks periodically download replacement hook code from the configured SolonGate API and atomically replace local hook files.
- The conversation hook posts redacted user and assistant text to the configured API when an API key is present.
- The audit hook sends tool names, argument summaries, and decisions to the API.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The agent-control changes occur through an explicit global setup command and require a SolonGate API key.
- The inspected network behavior is product-aligned telemetry and policy enforcement; no unrelated credential harvesting or stealth payload was found.
Source & flagged code
19 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@0.89.18.
See all versions of @solongate/proxy for other recorded verdicts.
- Review the evidence and your use of @solongate/proxy@0.89.18 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.