remove-ai-marks
Scrub AI provenance marks from text and files using the markscrub CLI: invisible Unicode (Layer A), optional statistical rewrite (Layer B), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/SVG/PDF/DOCX/HTML/MD. Use when the user asks to strip watermarks, remove Content Credentials, clean AI metadata, remove invisible Unicode, or run /remove-ai-marks.
anshaneja5 · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add anshaneja5/markscrub --skill remove-ai-marks技能说明
name: remove-ai-marks description: > Scrub AI provenance marks from text and files using the markscrub CLI: invisible Unicode (Layer A), optional statistical rewrite (Layer B), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/SVG/PDF/DOCX/HTML/MD. Use when the user asks to strip watermarks, remove Content Credentials, clean AI metadata, remove invisible Unicode, or run /remove-ai-marks.
Remove AI marks (markscrub)
Privacy / provenance hygiene for content the user owns.
Do not claim results are “human-written,” “undetectable,” or that they pass a vendor detector. Separate verifiable cleans from best-effort rewrites in every summary.
Setup
Prefer the project-local CLI:
# from the markscrub repo
npm install
npx tsx src/cli.ts help
# or after build:
npm run build && node dist/cli.js help
If markscrub is on PATH, use that instead.
Workflow
1. Inspect first
markscrub inspect path/to/file --json
Summarize Unicode hits and metadata/C2PA hints briefly.
2. Deterministic clean (Layer A + files)
markscrub clean INPUT -o OUTPUT --json
Always do this for matching inputs. Re-inspect OUTPUT when useful.
PDF cleaning needs exiftool on PATH; otherwise report that PDF was left unchanged.
3. Offer rewrite (Layer B) for prose
After clean, always offer a statistical-mark reduction pass for natural-language text. Do not skip silently.
# Default: print a strong paraphrase prompt (no API key required)
markscrub rewrite INPUT --backend print-prompt
# Local presets
markscrub rewrite INPUT -o OUT.md --backend ollama --model llama3.2
markscrub rewrite INPUT -o OUT.md --backend lmstudio
# OpenAI-compatible cloud
export MARKSCRUB_REWRITE_API_KEY=...
markscrub rewrite INPUT -o OUT.md --backend openai --strength paraphrase
Model hygiene: Prefer a rewrite model different from the suspected origin model.
Also useful:
markscrub inspect DIR --recursive --fail-on-findings --sarif out.sarif
markscrub clean DIR -o OUTDIR --recursive --diff
printf 'text' | markscrub clean - -o cleaned.txt
./scripts/install-skill.sh cursor
Then run Layer A again on the rewrite result (markscrub clean).
4. Report residual risk honestly
Use the JSON report fields:
findings[].verifiable— true for Unicode/metadata actionsresidualRisk— always mention sampling marks may remain
Ethics
Intended for the user’s own content (privacy, hygiene, research). If the user clearly wants academic fraud or illegal non-disclosure, warn and only perform technical cleaning on content they own.
References
references/mark-classes.md— Unicode / sampling / file provenancereferences/ethics.md— intended use