@livx.cc/agentx@0.99.47
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-aiInspected the manifest and flagged bundle locations. The lifecycle hooks, conditional Bodify credential retrieval, and explicit subagent setup do not establish malicious behavior.
Decision evidence
public snapshot- `package.json` has no preinstall, install, or postinstall hook; `prepare` only configures the repository hook path.
- The CLI sends a Bodify key only when `BODIFY_API_KEY` and `BODIFY_APP_ID` are set, using `BODIFY_URL` or the Bodify default.
- The CLI creates subagent files through the explicit `/agents new <name>` command; agent definitions are used as delegated prompts.
- The bundle loads project instruction files from the agent’s virtual filesystem; no install-time write to agent configuration was identified.
Source & flagged code
6 flagged · loading sourcePackage source references a known benign dynamic code generation pattern.
dist/index.jsView on unpkg · L5436Manifest-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@0.99.47.
See all versions of @livx.cc/agentx for other recorded verdicts.
- Review the evidence and your use of @livx.cc/agentx@0.99.47 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.