Humanizer Clark

PassAudited by ClawScan on May 12, 2026.

Overview

This is an instruction-only writing-editing skill that is mostly coherent, but users should review any rewritten files and note the package-name metadata mismatch.

This skill appears safe for ordinary text editing, but review changes before they are written to files, verify the package identity because the documented slug does not match the registry slug, and use the humanizing function only where it is appropriate to present AI-assisted writing as natural human prose.

Findings (3)

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.

Low

#ASI02: Tool Misuse and Exploitation

What this means

If invoked on files, the agent may rewrite documents rather than only producing suggested text.

Why it was flagged

The skill exposes file read/search and file write/edit tools. That is expected for a document-editing skill, but users should understand it may modify files.

Skill content

allowed-tools:
  - Read
  - Write
  - Edit
  - Grep
  - Glob
  - AskUserQuestion

Recommendation

Ask the agent to show proposed edits or diffs before applying changes, and keep backups of important documents.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

A user following the README outside the registry flow could install or reference a differently named package.

Why it was flagged

The README installation command references 'humanizer', while the registry entry under review is 'humanizer-clark'; _meta.json also uses slug 'humanizer'. This is a package-identity inconsistency, though no code or install script is present.

Skill content

clawdhub install humanizer

Recommendation

Verify the exact ClawHub slug and publisher before installing; maintainers should align README, _meta.json, SKILL.md, and registry metadata.

Low

#ASI09: Human-Agent Trust Exploitation

What this means

Using the skill may make AI-assisted writing harder for readers, teachers, reviewers, or organizations to recognize.

Why it was flagged

The core function is to make text appear more human-written. This is disclosed and purpose-aligned, but it can affect reader expectations about authorship.

Skill content

Remove signs of AI-generated writing from text... make it sound more natural and human-written

Recommendation

Use it consistently with any disclosure, academic, workplace, or publishing rules that apply to the text.