Agent skill · Audited from source

gemini-watermark-remover

skill · rookie-ricardo/erduo-skillsMIT licenceAudited 22 Oct 2026 · source 7e0764f5a97c

★ 938pushed 88 days ago
✓SAFEGrade B · 89/100 · 22 Oct 2026 · 7e0764f
938repo stars · whole rookie-ricardo/erduo-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 7e0764f5a97c and found no filesystem, network or shell access and no hard-coded secrets. What it does: Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “gemini-watermark-remover (rookie-ricardo/erduo-skills)”. Retrieved 22 Oct 2026. https://modelsatlas.com/skills/rookie-ricardo/gemini-watermark-remover

Trust audit

Audit 0.4.1 · source read 22 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesNot pinnedSome versions float
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS1
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

LOWSupply chainsupply.unpinned · scripts/requirements.txt
F-08 Supply chainCWE-829 · CWE-1357Layer L1
Pillow
Why
1 requirement(s) not pinned with ==
Fix
pin exact versions

Audit 0.4.1 · source sha 7e0764f5a97c · 22 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherrookie-ricardo GitHub userOwner of the repository this skill is read from
  • Source folderrookie-ricardo/erduo-skills/skills/gemini-watermark-removerThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict7e0764f5a97cA new audit runs when the source changes
  • Repository statusNot archivedLast push 88 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini…

---
name: gemini-watermark-remover
description: Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini watermark without HTML or server-side components.
---

# Gemini Watermark Remover

## Dependencies

- Python 3.9+
- Pillow (install with `pip install -r requirements.txt`)

## Quick start

1) Install dependencies in the scripts folder:
   - `cd skills/gemini-watermark-remover/scripts && pip install -r requirements.txt`
2) Run the CLI:
   - `python remove_watermark.py <input-image> <output-image>`

## CLI usage

- Parameters:
  - `input-image`: path to the Gemini watermarked image
  - `output-image`: path for the cleaned image (format inferred from extension)

Example:

```
python remove_watermark.py ./in.png ./out.png
```

## What this skill provides

- `scripts/remove_watermark.py`: CLI entry point and core algorithm.
- `assets/bg_48.png`, `assets/bg_96.png`: Pre-captured watermark alpha maps.
- `references/algorithm.md`: Math, detection rules, and limits.

## Workflow

1) Use `remove_watermark.py` for one-off processing.
2) If you need to adjust detection rules or alpha logic, read `references/algorithm.md`.

## Notes

- The script uses Pillow for image IO and per-pixel edits.
- Output format is inferred from the output file extension by Pillow.

Excerpt, first 1,432 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 7e0764f

Download folder ↗
git clone https://github.com/rookie-ricardo/erduo-skills
git -C erduo-skills checkout 7e0764f5a97c

The author documents no install command, so this uses the repository directly. Our verdict covers commit 7e0764f5a97c only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 7e0764f5a97c

Similar skills

Questions about gemini-watermark-remover

Is gemini-watermark-remover safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can gemini-watermark-remover access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (7e0764f5a97c), read on 2026-10-22. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.