Gemini Watermark Remover

Security checks across static analysis, malware telemetry, and agentic risk

Overview

Prompt-injection indicators were detected in the submitted artifacts (base64-block); human review is required before treating this skill as clean.

Before installing, be comfortable running local Python from this package, use a virtual environment for the dependencies, and review the full script if possible. Process only images you intend to edit, keep originals, and make sure removing or sharing images without the Gemini visible watermark is allowed for your use case. ClawScan detected prompt-injection indicators (base64-block), so this skill requires review even though the model response was benign.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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.

What this means

Installing dependencies from a compromised or unexpected package source could affect the local Python environment.

Why it was flagged

The skill relies on third-party Python packages with minimum versions rather than exact pins or hashes. This is normal for an image-processing tool, but package resolution is left to the user's environment.

Skill content
Pillow>=10.0.0
numpy>=1.24.0
Recommendation

Install from a trusted package index, preferably in a virtual environment, and consider pinning dependency versions if reproducibility matters.

What this means

The script can read the image file you provide and write an output image on your machine.

Why it was flagged

Using the skill involves running a local Python script. That is expected for this offline image-processing purpose, but it still executes local code with access to the chosen input and output paths.

Skill content
python3 scripts/remove_watermark.py photo.jpg
Recommendation

Run it only on files you intend to process, keep backups of important images, and inspect the full script if you are concerned about local code execution.

What this means

Using the output without proper permission or disclosure could mislead viewers or violate applicable rules.

Why it was flagged

The skill openly supports removing a visible AI watermark before sharing. This is not hidden behavior, but it has disclosure, trust, and possible terms-of-use implications.

Skill content
- Clean images before publishing or sharing
Recommendation

Use the tool only for images you are allowed to edit and share, and follow any relevant service terms, copyright rules, and disclosure requirements.