القائمة
LLM-specific security controls, prompt injection prevention, OWASP LLM Top 10
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/Hack23/homepage --skill owasp-llm-securityيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
عرض SKILL.md
استنادا إلى تصنيف SOC المهني
| name | OWASP LLM Security |
| description | LLM-specific security controls, prompt injection prevention, OWASP LLM Top 10 |
| license | Apache-2.0 |
| version | 1.0 |
| author | Hack23 AB |
| tags | ["owasp-llm","prompt-injection","llm-security"] |
| category | security |
| frameworks | ["OWASP LLM Top 10","ISO 27001:2022"] |
| related_policies | ["AI_Policy.md"] |
Enforce LLM-specific security controls aligned with OWASP LLM Top 10 2025.
Key Principle: "LLMs introduce unique security risks requiring specialized controls."
owasp_llm_top_10_controls:
llm01_prompt_injection:
input_validation:
- sanitize_user_input: remove_injection_attempts
- prompt_templates: use_parameterized_prompts
- context_isolation: separate_user_system_contexts
detection:
- monitor_outputs: alert_on_suspicious_responses
- log_inputs: track_all_prompts_for_analysis
- anomaly_detection: flag_unusual_input_patterns
llm02_insecure_output_handling:
output_validation:
- sanitize_before_render: html_encode_llm_outputs
- validate_format: check_expected_output_structure
- xss_prevention: never_trust_llm_generated_html
secure_integration:
- escaped_rendering:
prohibited_llm_practices:
- unvalidated_prompts: accepting_raw_user_input_to_llm
- trusting_outputs: using_llm_responses_without_validation
- no_rate_limits: allowing_unlimited_api_calls
- exposing_models: public_access_to_model_weights
- training_on_secrets: including_api_keys_in_training_data
- unmonitored_usage: no_logging_or_alerting_for_abuse
# Secure LLM Integration with Input Validation
import re
from typing import Optional
def sanitize_user_input(user_input: str) -> str:
"""Remove potential prompt injection attempts"""
# Remove system-like instructions
injection_patterns = [
r"ignore previous instructions",
r"disregard above",
r"you are now",
r"system:",
r"admin:",
]
cleaned = user_input
for pattern in injection_patterns:
cleaned = re.sub(pattern, "", cleaned, flags=re.IGNORECASE)
# Limit length to prevent token exhaustion
max_length = 500
cleaned = cleaned[:max_length]
return cleaned.strip()
def safe_llm_query(user_question: str) -> Optional[str]:
"""Safely query LLM with validated input"""
# Validate and sanitize input
sanitized_input = sanitize_user_input(user_question)
if not sanitized_input:
return "Invalid input detected"
# Use parameterized prompt template
system_prompt = "You are a helpful assistant. Answer factually and concisely."
user_prompt = f"User question: {sanitized_input}"
# Query LLM with separated contexts
response = query_llm(
system=system_prompt,
user=user_prompt,
max_tokens=150,
temperature=0.7
)
# Validate output before returning
if contains_suspicious_content(response):
log_security_event("Suspicious LLM output detected", response)
return "Response blocked for security reasons"
return html_escape(response) # XSS prevention
# LLM API Rate Limiting
from flask import Flask, request, jsonify
from flask_limiter import Limiter
from flask_limiter.util import get_remote_address
import time
app = Flask(__name__)
# Rate limiter configuration
limiter = Limiter(
app=app,
key_func=get_remote_address,
default_limits=["100 per hour", "10 per minute"],
storage_uri="redis://localhost:6379"
)
# Cost-based limiting
MAX_TOKENS_PER_REQUEST = 1000
MAX_COST_PER_USER_PER_DAY = 100 # USD
@app.route('/api/llm/query', methods=['POST'])
@limiter.limit("10 per minute")
def llm_query():
"""LLM API endpoint with comprehensive DoS protection"""
user_id = request.headers.get('X-User-ID')
user_input = request.json.get('prompt', '')
# Token limit enforcement
estimated_tokens = len(user_input.split()) * 1.3 # Rough estimate
if estimated_tokens > MAX_TOKENS_PER_REQUEST:
return jsonify({
"error": "Request exceeds maximum token limit"
}), 400
# Daily cost limit check
user_cost_today = get_user_cost_today(user_id)
if user_cost_today >= MAX_COST_PER_USER_PER_DAY:
return jsonify({
"error": "Daily cost limit exceeded"
}), 429
# Timeout enforcement
start_time = time.time()
timeout_seconds = 30
try:
response = query_llm_with_timeout(
user_input,
timeout=timeout_seconds
)
# Track usage cost
cost = calculate_usage_cost(user_input, response)
record_user_cost(user_id, cost)
return jsonify({
"response": response,
"cost": cost,
"remaining_daily_quota": MAX_COST_PER_USER_PER_DAY - user_cost_today
})
except TimeoutError:
return jsonify({
"error": "Request timed out"
}), 504
# Output Filtering to Prevent Data Leakage
import re
from typing import List, Tuple
# Patterns for sensitive data detection
SENSITIVE_PATTERNS = {
'api_key': r'[A-Za-z0-9]{32,}',
'email': r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}',
'ssn': r'\b\d{3}-\d{2}-\d{4}\b',
'credit_card': r'\b\d{4}[- ]?\d{4}[- ]?\d{4}[- ]?\d{4}\b',
'aws_key': r'AKIA[0-9A-Z]{16}',
}
def detect_sensitive_data(text: str) -> List[Tuple[str, str]]:
"""Detect potential sensitive data in LLM output"""
findings = []
for data_type, pattern in SENSITIVE_PATTERNS.items():
matches = re.findall(pattern, text)
for match in matches:
findings.append((data_type, match))
return findings
def redact_sensitive_data(text: str) -> str:
"""Redact sensitive data from LLM output"""
redacted = text
for data_type, pattern in SENSITIVE_PATTERNS.items():
redacted = re.sub(pattern, f"[REDACTED_{data_type.upper()}]", redacted)
return redacted
def safe_llm_output_handler(llm_response: str) -> dict:
"""Validate and sanitize LLM output before display"""
# Detect sensitive data
sensitive_findings = detect_sensitive_data(llm_response)
if sensitive_findings:
# Log security incident
log_security_event(
"Sensitive data detected in LLM output",
findings=sensitive_findings
)
# Redact sensitive data
safe_response = redact_sensitive_data(llm_response)
return {
"response": safe_response,
"warning": "Some content was redacted for security",
"redacted_count": len(sensitive_findings)
}
# HTML escape to prevent XSS
return {
"response": html_escape(llm_response),
"warning": None
}
Policies: AI Policy
Skills: ai-governance, secure-development, data-classification
Frameworks: OWASP LLM Top 10 2025, ISO 27001 A.14
