registry / @ziikoo/woa / 2.2.1

@ziikoo/woa@2.2.1

WOA remote-only CLI and hosted Web entrypoint for WeChat Official Account MCP SaaS

AI Security Review

scanned 12h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

User runs `woa mcp config codex|claude --server <url> --output <path>`.

Impact

A user-directed AI client can be configured to access the supplied remote MCP endpoint.

Mechanism

Explicit remote MCP client configuration generation.

Rationale

No concrete malicious chain, install hook, stealth persistence, or exfiltration was found by source inspection. The explicit AI-client configuration writer warrants a warn verdict under the firewall policy for user-command agent configuration mutation.

Evidence

package.jsondist/src/cli/woa.jsdist/src/index.jsdist/src/worker/media-tools.jsdist/src/worker/index.js~/.config/woa/cli.json

Network endpoints1

woa.ziikoo.app/mcp

Decision evidence

public snapshot

AI called this Suspicious at 88.0% confidence with false-positive risk.

@ziikoo/woa@2.2.1

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code