Bilingual AI Humanizer — Español & English
PassAudited by VirusTotal on May 11, 2026.
Overview
Type: OpenClaw Skill Name: bilingual-humanizer Version: 3.2.1 The bilingual-humanizer skill bundle is a legitimate tool designed to detect and mitigate AI-generated writing patterns in English and Spanish. The SKILL.md instructions are well-structured, guiding the agent to use the provided CLI/MCP tools and knowledge base files (knowledge/patterns-*.md) for text analysis without any evidence of harmful prompt injection or unauthorized data access. Notably, the package has zero production dependencies, reducing supply chain risk, and the SKILL.md includes a safety rule requiring explicit user confirmation before executing directory scans.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If the user approves a broad folder scan, the tool may process many local documents.
The skill can direct an agent to run local CLI/MCP tools against files and folders. This is aligned with text analysis, and the directory-scan instruction includes an explicit user-confirmation safeguard.
Ejecuta `humanizer analyze --json -f <archivo>` ... `humanizer scan` ... antes de ejecutar un escaneo sobre un directorio, muestra al usuario el path exacto y espera confirmación explícita.
Run it only on files or directories you intend to analyze, and confirm exact paths before any folder scan.
Installing the optional CLI or MCP server would execute code that was not reviewed in these artifacts.
The optional CLI/MCP path depends on external npm/GitHub code that is not included in the reviewed ClawHub artifact, although the README clearly discloses this and recommends review and pinning.
el CLI y el MCP server se instalan desde npm/GitHub y contienen código fuente que no forma parte del artefacto revisado en ClawHub. Revisa el repositorio ... y usa una versión pinada
If you use the CLI/MCP integration, inspect the npm package or GitHub repository first and pin the exact version you trust.