shield-security 0.5.0

SHIELD — Automated security layer for LLM-assisted web development

LLM Security in Web Applications

Emerging Threats, Vulnerability Taxonomies, and Mitigation Frameworks

Independent Academic Research — Ali Yasin Idrees — 2026

---

Overview

This repository contains the complete empirical research, implementation code, and validation results for an independent study comparing the security of web application code generated by three leading free-tier Large Language Models.

Model	Provider	Architecture
GPT-5 mini	OpenAI	RLHF / InstructGPT
Claude Sonnet 4.6	Anthropic	Constitutional AI
Gemini 3 Flash	Google DeepMind	Multimodal Transformer

20 standardized web development tasks generated 60 Python Flask and Node.js Express files, analyzed using Bandit 1.9.4 and Semgrep 1.155.0.

---

Key Findings

• 52 security findings across 60 generated files — zero files were completely clean
• debug=True (CWE-94) present in 27 of 30 Flask files across all three models
• Knowledge-Action Gap confirmed at 100% — all models warned against vulnerabilities they simultaneously generated
• Claude Sonnet 4.6 achieved the lowest vulnerability density: 1.89 I/100L (baseline) → 0.17 I/100L (after SHIELD Layer 3) — the study minimum
• SHIELD Layer 3 FDSP eliminated 100% of High-severity findings at K=1 across all models — 38 auto-remediations in a single automated pass

I/100L Vulnerability Density — All Conditions

Condition	GPT-5 mini	Claude S.4.6	Gemini 3 Flash	Average
Without SHIELD	4.96	1.89	6.00	4.28
With SHIELD Layer 1	1.44	1.02	1.02	1.16
With SHIELD Layer 3	1.16	0.17 ⭐	1.55	0.96
Total Reduction	77%	91%	74%	77% avg

I/100L (Issues Per 100 Lines) — a normalization metric introduced in this study to enable valid cross-model comparison by controlling for code verbosity differences.

---

SHIELD Framework

Secure Hybrid Integration and Enforcement Layer for LLM-assisted Development

A five-layer security architecture spanning the complete lifecycle of LLM-assisted web development.

┌──────┬──────────────────────────┬──────────────────────────────┐
│  L1  │  Prompt Engineering      │  SPT — 9 mandatory rules     │
│  L2  │  Generation Guidance     │  GRASP DAG — 8 SCP nodes     │
│  L3  │  Validation & Remediation│  FDSP — K=3 auto-fix engine  │
│  L4  │  Deployment Gate         │  GitHub Actions CI/CD        │
│  L5  │  Runtime Monitoring      │  WAF + Canary + JIT perms    │
└──────┴──────────────────────────┴──────────────────────────────┘

Layer	File	Status
Layer 1	Built into prompts	✅ Empirically Validated
Layer 2	shield_layer2_grasp.py	✅ Implemented
Layer 3	shield_layer3_fdsp.py	✅ Empirically Validated
Layer 4	.github/workflows/shield_layer4_gate.yml	✅ Live on this repo
Layer 5	shield_layer5_runtime.py	✅ Implemented

---

Repository Structure

llm-security-research/
│
├── .github/workflows/
│   └── shield_layer4_gate.yml        # SHIELD Layer 4 — CI/CD gate (LIVE)
│
├── snippets/                          # Generated code corpora
│   ├── chatgpt/                       # GPT-5 mini without SHIELD
│   ├── claude/                        # Claude S.4.6 without SHIELD
│   ├── gemini/                        # Gemini 3 Flash without SHIELD
│   ├── chatgpt_shield/                # GPT-5 mini with SHIELD Layer 1
│   ├── claude_shield/                 # Claude S.4.6 with SHIELD Layer 1
│   └── gemini_shield/                 # Gemini 3 Flash with SHIELD Layer 1
│
├── results/layer3_fdsp/
│   └── fdsp_master_results.json       # Layer 3 validation raw results
│
├── shield_layer2_grasp.py             # SHIELD Layer 2 — GRASP DAG
├── shield_layer3_fdsp.py              # SHIELD Layer 3 — FDSP engine
├── shield_layer5_runtime.py           # SHIELD Layer 5 — runtime monitoring
│
├── LLM_Security_Research_In_Web_Applications # Full research paper
├── LLM_Security_Research_FINAL.xlsx     # Results dashboard
└── README.md

---

Running the SHIELD Tools

Installation

# Clone the repository
git clone https://github.com/Aliidrees1234/llm-security-research
cd llm-security-research

# Install SHIELD as a CLI tool
pip install -e .

# Verify installation
shield version

---

Usage

# Scan a project for vulnerabilities
shield scan ./my_project

# Auto-fix vulnerabilities — safe copy
shield fix ./my_project --output ./fixed

# Auto-fix directly in place
shield fix ./my_project --inplace

# Maximum FDSP iterations
shield fix ./my_project --output ./fixed --k 3

---

Run Tests

pip install pytest
pytest tests/ -v

Expected output: 41 passed in 0.xx s

Layer 2 — GRASP DAG (Prompt Enhancer)

Analyzes a developer prompt and injects relevant SCP security constraints automatically.

from shield_layer2_grasp import GRASPEngine

engine = GRASPEngine()
prompt = "Write a Flask login endpoint with SQLite"
secured = engine.build_secured_prompt(prompt)
# Send secured to your LLM instead of the raw prompt

Layer 3 — FDSP Auto-Remediation

pip install bandit

python shield_layer3_fdsp.py \
  --corpora snippets/chatgpt snippets/claude snippets/gemini \
  --output results/layer3 \
  --k 3

Actual results from this study (April 6, 2026):

Corpus          K0 High   K1 High   K0 I/100L   K1 I/100L   Reduction
chatgpt/           11         0        3.30         1.16        100%
claude/            11         0        1.50         0.17        100%
gemini/             9         0        4.42         1.55        100%

Layer 5 — Runtime Monitoring

from flask import Flask
from shield_layer5_runtime import ShieldMiddleware

app = Flask(__name__)
shield = ShieldMiddleware(app, block_injections=True)
# Now protects against prompt injection, canary detection, JIT permissions

---

Research Contributions

1. Knowledge-Action Gap (Definition 2.1)

The first formal definition of the phenomenon where LLMs warn against vulnerabilities they simultaneously generate:

A model M exhibits the Knowledge-Action Gap with respect to vulnerability class V if: (a) M generates code containing instances of V when prompted for a web development task in V's scope; and (b) M's textual explanation includes explicit warnings against V.

Confirmed at 100% rate across all three models for debug=True.

2. I/100L Normalization Metric

Introduced to eliminate the verbosity confound in cross-model security comparison:

I/100L = (Total Issues ÷ Lines of Code) × 100

Without I/100L: GPT (17 issues) ≈ Claude (18 issues) — appears equal. With I/100L: GPT (4.96) vs Claude (1.89) — reveals 2.6× density difference.

3. FDSP K=1 Convergence

The engine was designed for up to K=3 iterations. All three models reached zero High-severity findings at K=1 — 38 automated fixes in a single pass.

4. Temporal Audit

Seven major LLM security citations were mis-dated (2026 instead of 2025). Corrected dates documented in Chapter 2. The year 2026 represents industrial adoption, not discovery.

---

Prompt Catalog

All 20 tasks contained zero security instructions — measuring intrinsic model behavior only.

ID	Framework	Primary CWE	Vulnerability Class
A01	Python Flask	CWE-94, CWE-259	debug=True, Hardcoded key
A02	Python Flask	CWE-89, CWE-639	SQL injection, IDOR
A03	Python Flask	CWE-434, CWE-22	Unrestricted upload, Path traversal
A04	Python Flask	CWE-916, CWE-20	Weak hashing, Input validation
A05	Python Flask	CWE-89	SQL injection via LIKE
A06	Python Flask	CWE-285, CWE-330	Broken access control
A07	Python Flask	CWE-259, CWE-640	Hardcoded credentials
A08	Python Flask	CWE-22, CWE-200	Path traversal, Info exposure
A09	Python Flask	CWE-79, CWE-327	XSS, Weak hash
A10	Python Flask	CWE-78	OS command injection / RCE
B01	Node.js Express	CWE-345	JWT algorithm confusion
B02	Node.js Express	CWE-943	NoSQL injection
B03	Node.js Express	CWE-22	Path traversal
B04	Node.js Express	CWE-916	Weak hashing
B05	Node.js Express	CWE-89/943	Injection via filter
B06	Node.js Express	CWE-79	Reflected XSS
B07	Node.js Express	CWE-78	OS command injection
B08	Node.js Express	CWE-620	Unverified password change
B09	Node.js Express	CWE-918	SSRF
B10	Node.js Express	CWE-79	Stored XSS

---

Tools & Scan Dates

Tool	Version	Scope	Scan Date
Bandit	1.9.4	Python Flask (all 6 corpora)	22 March 2026
Semgrep	1.155.0	Node.js Express (all 6 corpora)	25 March 2026
FDSP Engine	1.0	Python (3 without-SHIELD corpora)	6 April 2026

---

Citation

@misc{idrees2026llmsecurity,
  author    = {Idrees, Ali Yasin},
  title     = {LLM Security in Web Applications: Emerging Threats,
               Vulnerability Taxonomies, and Mitigation Frameworks},
  year      = {2026},
  publisher = {GitHub},
  url       = {https://github.com/Aliidrees1234/llm-security-research}
}

---

Author

Ali Yasin Idrees — Independent Researcher, 2026

---

This research was conducted independently, without institutional affiliation or external funding. SHIELD Layer 4 is live and protecting this repository — every push is automatically scanned.