Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Security & Compliance Pre-Scan Gate

A zero-trust gatekeeper skill that scans every incoming file or URL and returns a pass/reject verdict plus a compliance scan report before any document processing happens.

Security & ReviewIntermediate★ 6,083⑂ 585AI score 6/10Last updated: Sep 2, 2026

What it does

  • Takes a local file path (PDF/PPT/Excel/Word/image) or an external URL and issues a pass / reject verdict.
  • Combines a violating-domain blacklist (e.g. Sci-Hub), OA document licence checks, and python-magic file-type detection into a report with hit items and risk level.
  • Emits a trace_id so every scan is recorded as provenance for auditing.
  • Explicit fail-closed rules: scanner down, unknown file type, or unreadable blacklist all result in reject + alert, never a silent pass.

Who it's for

  • Engineers adding an intake checkpoint to RAG systems, internal knowledge bases, or contract-review pipelines.
  • Data pipeline owners who must block copyright/licence-violating sources.
  • Anyone designing a "gatekeeper" worker inside a multi-agent workflow.

Example uses

  1. Pass an uploaded PDF path as target; only forward it to parsing if the verdict is pass.
  2. Feed an external paper URL — if the domain is blacklisted, return reject with the reason in the report.
  3. Swap policy_ref to apply a finance or healthcare compliance baseline while reusing the same gate.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/anbeime/skill/HEAD/antinet-agentteams/skills/security-scan/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the antinet-agentteams/skills/security-scan folder from the GitHub repo anbeime/skill into my ~/.claude/skills/security-scan/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/anbeime/skill.git && mkdir -p ~/.claude/skills && cp -r skill/antinet-agentteams/skills/security-scan ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Run git clone https://github.com/anbeime/skill.git in your terminal.
  2. Create the skills folder: mkdir -p ~/.claude/skills.
  3. Copy the skill: cp -r skill/antinet-agentteams/skills/security-scan ~/.claude/skills/.
  4. Install the file-type dependency: pip install python-magic (on macOS also brew install libmagic).
  5. Provide your blacklist CSV/JSON and OA licence rule files inside the skill folder — if the repo doesn't ship them, you must create them.
  6. Restart Claude Code and ask something like "run a security scan on this file before processing".
  7. To try the bundled runner, execute python skills/security-scan/scripts/run_security_scan.py from the repo root and inspect the resulting JSON report.
View source on GitHub ↗