Hugging Face's logo

LayerFault
/
mcp-static-security-suite

layerfault
security-research
model-security
Synthetic
adversarial-testing
Model card Files
xet
 Community
mcp-static-security-suite / README.md
izm1chael's picture
izm1chael
Publish Layerfault synthetic corpus LF-CORPUS-MCP-0001
8e22559 verified
preview code
|
Raw
History Blame Contribute Delete
2.13 kB
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

mcp-static-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-MCP-0001

Purpose

Static MCP configuration combining plaintext transport, URL credentials, fake env credentials, overbroad scopes, unpinned npx, auto-confirm and contradictory tool annotation.

Direct expected Layerfault rules

  • LF-MCP-TLS-ABSENT
  • LF-MCP-CREDENTIAL-IN-URL
  • LF-MCP-CREDENTIAL-ENV-EXPOSURE
  • LF-MCP-SCOPE-OVERBROAD
  • LF-MCP-SUPPLY-CHAIN-AUTO-DOWNLOAD
  • LF-MCP-SUPPLY-CHAIN-AUTO-CONFIRM
  • LF-MCP-CONTRADICTORY-ANNOTATION
  • LF-MCP-TOKEN-PASSTHROUGH-RISK

Candidate rules

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

  • LF-MCP-AUTH-ABSENT
  • LF-MCP-AUTH-METADATA-MISSING
  • LF-MCP-TOKEN-AUDIENCE-UNBOUND
  • LF-MCP-ORIGIN-UNRESTRICTED

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.