_ _ _ ____ ___ ____ ____ _  _ ____ ____ _  _ ____    ____ ____ _  _ ____ _  _ ____ ____
| | | |__|  |  |___ |__/ |\/| |__| |__/ |_/  [__  __ |__/ |___ |\/| |  | |  | |___ |__/
|_|_| |  |  |  |___ |  \ |  | |  | |  \ | \_ ___]    |  \ |___ |  | |__|  \/  |___ |  \

watermarks-remover

Agent skill + stdlib Python scripts to strip multi-vendor AI provenance marks from text and files — for privacy and hygiene on content you own.

Layer	Target	How
A	Invisible Unicode, exotic spaces, bidi, tag chars	Deterministic Python scripts
B	Statistical (token-sampling) text watermarks	Agent rewrite + optional rewrite_text.py hook
Files	C2PA / EXIF / XMP / doc props	PNG, JPEG, SVG, PDF, DOCX, ODT, HTML, Markdown

Vendors / ecosystems (class-level): Claude, Gemini / SynthID-Text, OpenAI provenance surfaces, open-LLM Kirchenbauer-style marks.

Latest release: v0.1.0

Skill path: skills/remove-ai-marks/
(migration: formerly remove-claude-marks; slash alias /remove-claude-marks still documented)

Install (agent skill)

# Grok Build / project-local
mkdir -p .grok/skills
ln -sfn "$(pwd)/skills/remove-ai-marks" .grok/skills/remove-ai-marks

# User-global Grok
mkdir -p ~/.grok/skills
ln -sfn "$(pwd)/skills/remove-ai-marks" ~/.grok/skills/remove-ai-marks

Invoke with /remove-ai-marks or ask to “strip AI watermarks / C2PA / Claude marks / SynthID-class text.”

Optional system tools (auto-used when present):

Tool	Role
c2patool	Inspect C2PA manifests
exiftool	Residual metadata strip (esp. PDF)

Core scripts need Python 3.10+ stdlib only. Layer B model calls are optional.

Quick use (scripts)

SCRIPTS=skills/remove-ai-marks/scripts

# Unified inspect / clean
python3 "$SCRIPTS/inspect_file.py" draft.md
python3 "$SCRIPTS/clean_file.py" draft.md -o draft.cleaned.md
python3 "$SCRIPTS/clean_file.py" photo.png -o photo.cleaned.png
python3 "$SCRIPTS/clean_file.py" notes.docx -o notes.cleaned.docx

# Text Layer A
python3 "$SCRIPTS/inspect_text.py" draft.md
python3 "$SCRIPTS/clean_text.py" draft.md -o draft.cleaned.md --stats

# Layer B rewrite hook (default: print prompt only — no model required)
python3 "$SCRIPTS/rewrite_text.py" draft.md --backend print-prompt --strength paraphrase
# Optional local Ollama:
# WATERMARKS_REWRITE_BACKEND=ollama WATERMARKS_REWRITE_MODEL=llama3.2 \
#   python3 "$SCRIPTS/rewrite_text.py" draft.md -o draft.rewritten.md

# Images
python3 "$SCRIPTS/inspect_image.py" shot.png
python3 "$SCRIPTS/clean_image.py" shot.png -o shot.cleaned.png

Coverage matrix

Channel	Claude	Gemini/SynthID	OpenAI	Open-LLM
Unicode / edit-based text	Layer A	Layer A	Layer A	Layer A
Statistical sampling text	Layer B best-effort	Layer B best-effort	Layer B if present	Layer B best-effort
C2PA / file metadata	Yes (listed formats)	Yes when present	Yes when present	Yes when present
Pixel image marks	Out of scope	Out of scope	Out of scope	Out of scope
Training backdoors	Out of scope	Out of scope	Out of scope	Out of scope

Details: skills/remove-ai-marks/references/vendor-notes.md, mark-classes.md.

---

How text marking works (short)

Modern LLM watermarks often hide a signal in which tokens are chosen (generative / sampling bias), not only in invisible characters. Edit-based schemes inject Unicode or synonym rules. File schemes attach C2PA or generator metadata.

• Layer A removes edit-based Unicode carriers (testable).
• Layer B attacks sampling watermarks via heavy rewrite (best-effort; literature-standard attacks such as paraphrase / back-translation).
• File cleaners strip C2PA/XMP/props from supported containers.

Until vendors ship public detectors and keys, no tool can honestly certify “this fails the official check.” Reports must separate verifiable vs best-effort work.

Prefer a non-origin model for Layer B (do not rewrite Claude text with Claude if you are trying to avoid re-stamping).

---

File formats

Format	Inspect	Clean
PNG / JPEG	C2PA chunks / APP11, AI XMP hints	Drop metadata segments
SVG	<metadata>, XMP	Strip blocks
PDF	Byte/XMP + optional tools	exiftool preferred; degraded without it
DOCX	docProps / customXml	Scrub props, drop customXml
ODT	meta.xml	Drop generator / AI-ish meta
HTML	meta, JSON-LD, data-ai*	Strip tags/attrs
Markdown	YAML frontmatter AI keys	Drop keys + Layer A body

Pixel-domain watermarks and C2PA soft binding (in-content watermark that can re-link a remote Content Credentials manifest after metadata is stripped) remain out of scope. Stripping hard-bound C2PA does not clear those channels.

Residual risk after a clean

This tool reports verifiable removals (Unicode counts, metadata actions) and best-effort Layer B rewrites. It cannot certify that vendor detectors will fail.

To check residual signals yourself (optional, external):

Channel	What we remove	What may remain	External check (examples)
Hard-bound C2PA / EXIF / XMP	Yes	Soft-bound / pixel marks	c2patool, Content Credentials verify
SynthID-class media	No	Pixel/audio/video watermark	Provider tools (e.g. Google SynthID / Vertex detector where offered)
Statistical text	Best-effort rewrite	Strong marks after light edit	No public universal detector; vendor tools when available

Industry two-layer context (C2PA + imperceptible watermark): Institute of AI PM guide.

---

Removal options (summary)

Option	Removes	Notes
Unicode scrub (Layer A)	ZWSP, bidi, tags, exotic spaces, …	Safe default for text
Rewrite (Layer B)	Statistical token marks (best-effort)	Always offered by skill
Container/metadata strip	File provenance	See format table
Open-weight local models	Avoid re-stamping with origin model	Operational alternative

Matrix: skills/remove-ai-marks/references/removal-matrix.md.

Ethics

See skills/remove-ai-marks/references/ethics.md. For privacy and research on your content — not academic fraud or false “human-written” claims.

Tests

python3 -m venv .venv && .venv/bin/pip install pytest
.venv/bin/python -m pytest          # or: make test
make smoke                          # quick CLI smoke on fixtures

Changelog

v0.1.0 — packaging polish + provenance honesty

• Makefile (test / smoke / install-skill) and pytest.ini
• Fixture samples for Markdown, HTML, SVG; PDF degraded-clean test
• Docs: industry two-layer model (hard-bound C2PA vs soft binding / SynthID-media)
• README residual-risk table + links to external verify tools
• Reference: Institute of AI PM C2PA/SynthID guide
• Soft-binding and pixel/audio/video watermarks explicitly out of scope in skill/matrix/ethics

v0.0.1 — initial multi-vendor release

• Agent skill remove-ai-marks (replaces Claude-only remove-claude-marks)
• Layer A: invisible Unicode / bidi / tag chars / space homoglyphs (inspect_text / clean_text)
• Layer B: rewrite guidance + optional rewrite_text.py (print-prompt, Ollama, OpenAI-compatible)
• Files: C2PA/AI metadata strip for PNG, JPEG, SVG, PDF, DOCX, ODT, HTML, Markdown
• Unified inspect_file.py / clean_file.py
• Multi-vendor docs (Claude, Gemini/SynthID-class, OpenAI, open-LLM)
• Stdlib-first scripts; optional c2patool / exiftool

License

MIT — see LICENSE.

References

• How Claude marks AI-generated content (Anthropic)
• Dathathri et al., Scalable watermarking for identifying large language model outputs (SynthID-Text, Nature 2024)
• C2PA / c2patool
• Kirchenbauer et al., A Watermark for Large Language Models
• google-deepmind/synthid-text (research reference; not used for detection here)
• Institute of AI PM, AI Content Provenance and Watermarking: The PM's Guide to C2PA and SynthID (two-layer industry model: C2PA + imperceptible watermark / soft binding; SB 942 / EU AI Act Art. 50 context)