README.md

metadata

license: apache-2.0
tags:
  - layerfault
  - security-research
  - model-security
  - synthetic
  - adversarial-testing
extra_gated_prompt: >-
  This repository is a synthetic security-test artifact from the Layerfault
  corpus. It intentionally contains adversarial characteristics (e.g. suspicious
  pickle opcodes, executable-format smuggling, prompt-injection strings)
  designed to exercise security scanner detection rules. It is **not** a usable
  ML model and must never be loaded or executed outside an isolated
  scanner-testing environment. By accepting, you confirm you understand this
  repository is a test fixture, not production model weights.
extra_gated_button_content: I understand this is a security test fixture and accept the risk
gated: auto

tokenizer-security-suite

SECURITY TEST ARTIFACT: DO NOT USE AS A PRODUCTION MODEL

This repository is part of the Layerfault synthetic security corpus. It is deliberately constructed to contain security-relevant characteristics for scanner testing.

Corpus ID: LF-CORPUS-TOK-0001

Purpose

Clean and manipulated tokenizer variants for EOS/BOS, hidden prompt, role remap, role-boundary and tool-template comparisons.

Direct expected Layerfault rules

• None; this repository is a control/comparison input.

Candidate rules

These are deliberately plausible targets that remain marked as candidates until the exact Layerfault build used for certification confirms them.

• LF-TOKENIZER-EOS-BOS-CONFLICT
• LF-TOKENIZER-HIDDEN-PROMPT
• LF-TOKENIZER-ROLE-BOUNDARY-CONTROL
• LF-TOKENIZER-ROLE-REMAP
• LF-TOKENIZER-SECURITY-DELTA
• LF-TOKENIZER-TOOL-TEMPLATE-RISK

Negative-control rules

These should remain silent for this corpus item.

• None

Safety

The corpus uses fake secrets, loopback/.invalid network destinations, harmless marker output, and synthetic model behavior only. It is intended for static scanning and isolated security testing.