Skip to content
Agentmart
Submit a tool

pleading-injection-guard

Detects prompt injection hidden in documents from the other side (pleadings, skeletons, bundles, served evidence, opponents' emails and attachments) before an…

Skill by lawve-ai

IndexedNOASSERTION★ 895
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/lawve-ai-pleading-injection-guard

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Detects prompt injection hidden in documents from the other side (pleadings, skeletons, bundles, served evidence, opponents' emails and attachments) before an AI reads them, so the model is not turned against your client. Checks word by word that the text an extractor hands the model was visibly drawn on the page: white, near-white, covered, clipped, off-page, tiny, transparent and invisible-mode text in PDF (ink test plus OCR); Word formatting resolved as Word does (styles, shading, theme colours, scaling, off-page frames, fallbacks, unused headers); HTML/CSS, RTF, email with attachments and zips, xlsx/pptx and legacy formats. Flags Unicode smuggling, text addressed to an AI and authorities found only in hidden text. Fails closed. Optional Read-tool hook. Use BEFORE any AI summary or analysis of an opposing or third-party document. Triggers: 'scan for injection', 'is this document safe', 'check the other side's skeleton', 'injection guard'.

Use cases: documents, spreadsheets, presentations, frontend

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/pleading-injection-guard

What's inside

Skill name
pleading-injection-guard
Description
Detects prompt injection hidden in documents from the other side (pleadings, skeletons, bundles, served evidence, opponents' emails and attachments) before an AI reads them, so the model is not turned against your client. Checks word by word that the text an extractor hands the model was visibly drawn on the page: white, near-white, covered, clipped, off-page, tiny, transparent and invisible-mode text in PDF (ink test plus OCR); Word formatting resolved as Word does (styles, shading, theme colours, scaling, off-page frames, fallbacks, unused headers); HTML/CSS, RTF, email with attachments and zips, xlsx/pptx and legacy formats. Flags Unicode smuggling, text addressed to an AI and authorities found only in hidden text. Fails closed. Optional Read-tool hook. Use BEFORE any AI summary or analysis of an opposing or third-party document. Triggers: 'scan for injection', 'is this document safe', 'check the other side's skeleton', 'injection guard'.
License
NOASSERTION
Instructions
96 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • name: "pleading-injection-guard" does not match folder "pleading-injection-guard-matei-clej"

Files (25)

  • .gitignore
  • LICENSE
  • README.md
  • SKILL.md
  • SUBMISSION.md
  • TESTING.md
  • hook.py
  • __init__.py · pig/
  • containers.py · pig/
  • core.py · pig/
  • docx.py · pig/
  • engine.py · pig/
  • html.py · pig/
  • pdf.py · pig/
  • rtf.py · pig/
  • scan.py
  • clean.docx · tests/fixtures/
  • clean.pdf · tests/fixtures/
  • hostile.docx · tests/fixtures/
  • hostile.html · tests/fixtures/
  • hostile.pdf · tests/fixtures/
  • make_fixtures.py · tests/
  • run_attacks.py · tests/
  • run_tests.sh · tests/
  • test_hook.py · tests/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from lawve-ai/awesome-legal-skills

Compare and alternatives

    Featured in

    Signals

    Stars
    895
    Forks
    119
    Open issues
    7
    Last commit (this folder)
    Oct 2, 2026 (26 days ago)

    From GitHub (fetched Oct 24, 2026).

    Details

    License
    NOASSERTION
    Repository
    github.com/lawve-ai/awesome-legal-skills
    Website
    lawve.ai
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Source
    GitHubgithub-graphql

    More from lawve-ai

    Cite this page

    pleading-injection-guard skill. Agent Mart. https://agentmart.dev/skills/lawve-ai-pleading-injection-guard (last updated 2026-10-24)