@livx.cc/agentx@0.99.106
Edge-native AI agent runtime — drives a virtual filesystem via any LLM (ai.libx.js). Same bytes run in node, browser, or edge.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe inspected lifecycle scripts do not reveal a consumer install-time attack, and the flagged CLI behavior aligns with configured provider access. Agent integration locations and child-process support are consistent with documented runtime features; no concrete malicious behavior was established.
Decision evidence
public snapshot- package.json has a prepare hook that sets the Git hooks path and a prepublishOnly build command; neither is a consumer install hook that performs the flagged behavior.
- The CLI uses configured provider keys and retrieves Bodify secrets only when Bodify credentials are provided, from the Bodify endpoint.
- The shell module exposes child-process execution as part of its shell tool; the inspected code does not establish a separate attack behavior.
- The inspected agent integration locations describe project instructions, subagent definitions, and Git worktree paths.
Source & flagged code
12 flagged · loading sourcePackage source references child process execution.
dist/tools.shell.jsView on unpkg · L891Findings
Affected versions and remediation
This report applies to @livx.cc/agentx@0.99.106.
See all versions of @livx.cc/agentx for other recorded verdicts.
- Review the evidence and your use of @livx.cc/agentx@0.99.106 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.