Gemini Watermark

PassAudited by ClawScan on May 1, 2026.

Overview

The artifacts describe a local, user-run image-processing tool that matches its stated watermark-removal purpose, with only minor dependency and responsible-use considerations.

This appears to be a straightforward local image-processing skill. Before installing, use a trusted Python environment, keep originals/backups, and consider whether removing a visible AI watermark is allowed for your intended use.

Findings (2)

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

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

Installing dependencies may fetch external packages, so the user is trusting the package index and current package versions.

Why it was flagged

The setup uses third-party Python packages without pinned versions. This is disclosed and normal for a Python image tool, but users should install from a trusted package source.

Skill content

pip install Pillow numpy

# Recommended: use uv for faster, isolated installs
uv pip install Pillow numpy

Recommendation

Install in a virtual environment from a trusted package index, and pin or review dependency versions if reproducibility matters.

Low

#ASI09: Human-Agent Trust Exploitation

What this means

Shared images may no longer visibly indicate their AI-generated origin.

Why it was flagged

The tool is explicitly intended to remove a visible AI watermark before sharing, which can reduce visible provenance cues for viewers.

Skill content

Clean images before publishing or sharing

Recommendation

Use only where you have permission and follow any applicable disclosure, platform, or provenance requirements.