@solongate/proxy@0.90.25
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 package is not proven malicious because it has no automatic npm lifecycle trigger and its privileged setup is user-invoked. Its broad multi-client hook registration, vendor-controlled self-update path, and cloud reporting create a meaningful extension-lifecycle risk that warrants a warning.
Decision evidence
public snapshot- Its global installer replaces hooks for Claude Code, Codex, Antigravity, and OpenCode, then locks the affected files.
- The installed guard periodically fetches hook source from the vendor API and atomically replaces local hook files; the hash is supplied with the same response.
- The conversation hook sends redacted user prompts and assistant replies to the vendor API when a global API key is configured.
- package.json contains no preinstall, install, postinstall, or other npm lifecycle hook.
- The installer is reached through interactive CLI functionality and rejects detected AI or non-interactive callers.
- The inspected network traffic is directed to the package vendor's configured API, not an unrelated host.
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@0.90.25.
See all versions of @solongate/proxy for other recorded verdicts.
- Review the evidence and your use of @solongate/proxy@0.90.25 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.