A3S-Lab

Exfiltration Triage — Data skill for Claude Code

Data community

Judge whether outbound content or an egress connection is a real data-exfiltration attempt.

How to install Exfiltration Triage

Installs to ~/.claude/skills/a3s-lab-sentry-exfiltration-triage/SKILL.md

Terminal

mkdir -p ~/.claude/skills/a3s-lab-sentry-exfiltration-triage && curl -fsSL https://raw.githubusercontent.com/A3S-Lab/Sentry/HEAD/skills/exfiltration-triage.md -o ~/.claude/skills/a3s-lab-sentry-exfiltration-triage/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Exfiltration Triage does

name: exfiltration-triage description: Judge whether outbound content or an egress connection is a real data-exfiltration attempt.

Exfiltration triage

Use this when L1/L2 flagged outbound content (`SslContent`) or a connection (`Egress`) as possibly leaking secrets or data.

What to establish

What is leaving. Distinguish a credential/secret (private key, API token, password, large base64 blob, customer PII) from an ordinary request body that merely contains the word "tok

Alternatives in Data

Privacy & Data Handling — This repository contains: - a plugin package (plugins/compound-engineering) made of markdown/config content 10.8k ★
Context Mode — Benchmark Results — Benchmarked against real outputs from popular Claude Code MCP servers, Skills, and dev tools 5.6k ★
HTML Video — Programmatic video for coding agents — HTML to video on your laptop 4.5k ★