@solongate/proxy@0.89.81
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-aiNo automatic npm lifecycle attack is present, so the evidence does not establish malicious install-hook abuse. The user-enabled global hook system nevertheless has a material remote-update and audit-exfiltration risk.
Decision evidence
public snapshot- The guard downloads hook content from the service and atomically replaces executable hook files during agent activity.
- An explicit global setup path writes hook handlers into Codex and other agent configuration locations.
- Denied tool-call records, including supplied tool arguments, are sent to the service unless local-only logging is enabled.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The agent-hook installation code is reached through package commands rather than npm installation.
- The remote endpoints are consistent with the package's named service.
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@0.89.81.
See all versions of @solongate/proxy for other recorded verdicts.
- Review the evidence and your use of @solongate/proxy@0.89.81 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.