Skip to content

shagghiesuperstar/veilbreaker

v0.3.0MIT

Deterministic, zero-dependency coverage of the latest documented (2025–2026) prompt-injection concealment and exfiltration TTPs. Built to pair with an ML classifier.

GitHubOpen Website
skills

step-0-untrusted-content

ALWAYS FIRST. Use whenever the bot reads web pages, emails, files, MCP tool output, or other bots' messages, and before any send, post, render, fetch-with-params, or data-carrying tool call. Routes untrusted content through VeilBreaker.

Read SKILL.md at the source

Pinned to revision 354e961c8fe1, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.