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.

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

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    │
└──────┴──────────────────────────┴──────────────────────────────┘

Repository Structure

llm-security-research/
│── .github/workflows
|     ├──shield_layer4_gate.yml
├── shield/                   
│   ├── cli.py
│   ├── reporter.py
│   ├── config.py
│   ├── layer2_grasp.py
│   ├── layer3_fdsp.py
│   ├── layer5_runtime.py
│   └── rules/
│       └── custom_rules.py
│
├── research/                  ← all research data
│   ├── paper/
│   ├── snippets/
│   └── results/
│
├── tests/                     ← all tests
├── docs/                      ← NEW: documentation
│   ├── rules.md               ← explain every rule
│   ├── pipeline.md            ← explain L2+L3 flow
│   └── api.md                 ← developer API reference
│
├── examples/                  ← NEW: real usage examples
│   ├── flask_login.py         ← vulnerable → fixed demo
│   └── node_download.js       ← vulnerable → fixed demo
│
├── setup.py
├── README.md

Running the SHIELD Tools

Installation

git clone https://github.com/Aliidrees1234/llm-security-research
cd llm-security-research
pip install -e .

Usage

# Scan a project
shield scan ./my_project

# Scan with HTML report
shield scan ./my_project --report report.html

# Scan quietly (High/Medium only)
shield scan ./my_project --quiet

# Auto-fix vulnerabilities
shield fix ./project` | Auto-fix Python vulnerabilities (Python only) |
shield fix ./my_project --output ./fixed --k 3

# Fix with report
shield fix ./my_project --output ./fixed --report after.html

# Compare before and after
shield compare before.json after.json --report comparison.html

# Initialize config file
shield init

# Show version
shield version

# Show doctor
shield doctor` | Check all dependencies and installation health |

# Full pipeline — prompt → generate → scan → fix
shield secure "Write a Flask login endpoint with SQLite"

# Secure prompt 
shield secure "Write a Flask login endpoint"

# Runtime monitor self-test
shield monitor --test

# Show WAF rules
shield monitor --show-rules

# Show shield dashboard
shield dashboard

## Security Auditing
# Generate Audit
shield audit ./project --company "Acme BV"` | Generate professional client audit report 

SHIELD can generate professional audit reports suitable for client engagements.


```bash
# Basic audit
shield audit ./my_project --company "Acme BV"

# Full audit with custom auditor name and output file
shield audit ./my_project \
  --company "Acme BV" \
  --auditor "Ali Yasin Idrees" \
  --output acme_audit_2026.html

# Open the report
start acme_audit_2026.html

The audit report includes:

• Executive summary with security grade
• Overall risk level (Low / Medium / High / Critical)
• I/100L vulnerability density score
• All findings with file, line, CWE reference, and remediation advice
• Remediation priority table
• Automated fix instructions

Suitable for delivering to clients as a standalone confidential document.

Language Support:

• shield fix — Python only (AST-based auto-remediation)
• shield scan — 8 languages (Python, JS, TS, C#, Java, PHP, Go, Ruby)
• shield audit — 8 languages (professional report for any language)

Multi-language auto-fix is planned for a future release.

Run Tests

pip install pytest
pytest tests/ -v
# 99 tests passing

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
---
# Generate security-hardened prompt for any LLM
shield prompt "Write a Flask login endpoint"

# Copy directly to clipboard
shield prompt "Write a Flask login endpoint" --copy

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.

5. Supply Chain Attack Detection (2026)

Two new rules targeting the 2026 wave of registry poisoning attacks:

• CUSTOM_UNICODE_OBFUSCATION — detects zero-width Unicode characters (TrapDoor campaign)
• CUSTOM_INSTALL_EXEC — detects module-level execution at import time

Prompt Catalog

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

Tools & Scan Dates

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.