@livx.cc/agentx@0.99.38
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-aiThis is a powerful agent runtime, but the risky primitives are explicit runtime functionality rather than install-time or covert behavior. The inspected source does not substantiate the scanner's claimed credential redirection or persistence.
Decision evidence
public snapshot- The CLI exposes a Shell tool capable of executing supplied commands.
- The CLI can send a supplied Bodify credential to its configured service when both Bodify environment variables are set.
- The manifest has a prepare hook that changes the local Git hooks path.
- There is no preinstall, install, or postinstall lifecycle hook.
- The Bodify request is gated on two explicitly configured environment variables.
- No source evidence shows secret harvesting, covert exfiltration, or automatic foreign agent-control-surface changes.
- Shell output and child environments apply secret redaction/filtering.
Source & flagged code
6 flagged · loading sourcePackage source references a known benign dynamic code generation pattern.
dist/index.jsView on unpkg · L5057Manifest-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@0.99.38.
See all versions of @livx.cc/agentx for other recorded verdicts.
- Review the evidence and your use of @livx.cc/agentx@0.99.38 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.