@livx.cc/agentx@0.99.37
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 1mo ago · by lpm-firewall-aiThe package is a feature-rich coding-agent runtime, including shell execution and optional credentialed services, but inspection found no install-time payload, self-dependency chain, credential redirection, or unconsented broad control-surface mutation. The prepare hook is limited to a Git hooks-path setting and does not establish the required malicious lifecycle chain.
Decision evidence
public snapshot- The CLI exposes user-invoked shell execution.
- The CLI can fetch secrets only when its Bodify credentials are already set.
- Its prepare script changes the local Git hooks path when that script runs.
- package.json has no preinstall, install, or postinstall hook.
- There is no runtime dependency on this package itself.
- No source-backed credential redirect or automatic foreign agent-config mutation was found.
Source & flagged code
6 flagged · loading sourcePackage source references a known benign dynamic code generation pattern.
dist/index.jsView on unpkg · L5047Manifest-reachable source sends a prompted API credential to a fixed unofficial gateway and persists the redirection.
dist/cli.jsView on unpkgFindings
Affected versions and remediation
This report applies to @livx.cc/agentx@0.99.37.
See all versions of @livx.cc/agentx for other recorded verdicts.
- Review the evidence and your use of @livx.cc/agentx@0.99.37 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.