@livx.cc/agentx@0.99.40
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 2mo ago · by lpm-firewall-aiThe observed network credential use is gated by explicit configuration, while shell execution is the stated runtime capability of a user-invoked coding agent. The package has no registry install lifecycle hook or concrete malicious chain.
Decision evidence
public snapshot- The CLI can retrieve configured Bodify secrets using a bearer credential.
- The coding-agent shell tool can execute user-directed commands.
- The manifest prepare hook changes the checkout Git hook path.
- There are no preinstall, install, or postinstall hooks.
- The Bodify request requires both user-supplied environment variables and allows its base URL to be overridden.
- No self-dependency, hidden payload, automatic credential harvesting, or automatic external control-surface mutation was found.
Source & flagged code
6 flagged · loading sourcePackage source references a known benign dynamic code generation pattern.
dist/index.jsView on unpkg · L5234Manifest-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@0.99.40.
See all versions of @livx.cc/agentx for other recorded verdicts.
- Review the evidence and your use of @livx.cc/agentx@0.99.40 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.