@livx.cc/agentx@0.99.30
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 14d ago · by lpm-firewall-aiThe source confirms conditional credential forwarding to an unrestricted environment-configured endpoint, which warrants a warning under the credential-forwarding policy. No inspected source establishes covert theft or a separate block-level attack.
Decision evidence
public snapshot- At CLI startup, the package reads BODIFY_API_KEY and sends it as a bearer token to a URL controlled by BODIFY_URL, defaulting to bodify.bod.ee; no destination restriction is shown.
- The manifest has no npm install hook; prepare only configures a Git hook path, while prepublishOnly builds the package.
- The inspected agent integration locations describe Claude-style worktrees, typed subagents, and loading project instruction files.
- The Bodify credential forwarding runs only when both BODIFY_API_KEY and BODIFY_APP_ID are present.
- Agent instruction loading reads repository files into the runtime; the cited integration locations do not show automatic plugin installation or broad agent configuration mutation.
Source & flagged code
6 flagged · loading sourcePackage source references a known benign dynamic code generation pattern.
dist/index.jsView on unpkg · L4868Manifest-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@0.99.30.
See all versions of @livx.cc/agentx for other recorded verdicts.
- Review the evidence and your use of @livx.cc/agentx@0.99.30 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.