@respira/wordpress-mcp-server@8.4.19
WordPress MCP server + companion plugin giving AI native access to page builder content, not just the REST API. 248 tools, 352 with WooCommerce, 17 page builders and the Site Editor. Element-level edits, full page creation, HTML to builder conversion, sna
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe manifest declares no install lifecycle hook, and the inspected agent configuration and skill writes are activated through explicit CLI commands. The cited network request is a documentation search, while the inspected chat hygiene code redacts credential-like content; no concrete attack behavior was established.
Decision evidence
public snapshot- package.json exposes setup and skill installation as CLI binaries; no install lifecycle hook is declared.
- The configuration file is written as package configuration, and the flagged configuration precedence concerns the package's own settings.
- Skill installation parses explicit command-line arguments and copies bundled skills only when the CLI is run.
- Agent client configuration is installed through an explicit command requiring a selected client; the setup code merges configuration into that client's config file.
- Chat hygiene redacts credential-like content before it is returned.
- The inspected server network call uses a configurable base URL for documentation search and sends a search query; no credential forwarding is shown.
Source & flagged code
6 flagged · loading sourceManifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.
dist/install-skills.jsView on unpkgFindings
Affected versions and remediation
This report applies to @respira/wordpress-mcp-server@8.4.19.
See all versions of @respira/wordpress-mcp-server for other recorded verdicts.
- Review the evidence and your use of @respira/wordpress-mcp-server@8.4.19 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.