@solongate/proxy@0.90.61
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-aiThere is no automatic npm lifecycle trigger, but the package creates a broad, persistent agent-hook surface on an explicit command and remotely updates executable code. This is a concrete high-risk capability requiring a warning rather than proof of malicious installation-time behavior.
Decision evidence
public snapshot- An explicit global setup writes hooks into Claude, Codex, Antigravity, and OpenCode control surfaces.
- Installed hooks fetch and replace executable hook files from the vendor API without a pinned publisher signature.
- The conversation hook sends user prompts and assistant replies to the vendor API when a configured API key is present.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The global installer is reached through interactive CLI management commands, not package import or installation.
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@0.90.61.
See all versions of @solongate/proxy for other recorded verdicts.
- Review the evidence and your use of @solongate/proxy@0.90.61 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.