sickn33/agentic-awesome-skills/ai-agent-security

import re
from dataclasses import dataclass
from enum import Enum
class RiskLevel(Enum):
    LOW = "low"
    MEDIUM = "medium"
    HIGH = "high"
    CRITICAL = "critical"
@dataclass
class ValidationResult:
    is_safe: bool
    risk_level: RiskLevel
    matched_rules: list[str]
    sanitized_input: str
INJECTION_PATTERNS = [
    (r"ignore\s+(all\s+)?(previous|prior|above)\s+(instructions|prompts|rules)", "instruction_override"),
    (r"you\s+are\s+now\s+(a|an|the)\s+", "role_hijack"),
    (r"system\s*:\s*", "system_prompt_inject"),
    (r"<\|?(system|im_start|endoftext)\|?>", "control_token_inject"),
    (r"\[INST\]|\[\/INST\]|<<SYS>>", "template_inject"),
    (r"(?:execute|run|eval)\s*\(", "code_execution_attempt"),
    (r"(?:curl|wget|nc|ncat)\s+", "network_command_inject"),
    (r"(?:rm\s+-rf|mkfs|dd\s+if=|chmod\s+777)", "destructive_command"),
    (r"(?:\/etc\/passwd|\/etc\/shadow|\.env\b|\.ssh\/)", "path_traversal"),
    (r"(?:BEGIN\s+(?:RSA|DSA|EC)\s+PRIVATE\s+KEY)", "secret_exfil_attempt"),
]
def validate_agent_input(user_input: str, max_length: int = 4096) -> ValidationResult:
    """Validate and sanitize input before passing to agent."""
    matched = []
    risk = RiskLevel.LOW
    # Length check
    if len(user_input) > max_length:
        matched.append("input_too_long")
        risk = RiskLevel.MEDIUM
    # Null byte and control character removal
    sanitized = user_input.replace("\x00", "")
    sanitized = re.sub(r"[\x01-\x08\x0b\x0c\x0e-\x1f]", "", sanitized)
    # Pattern matching
    for pattern, rule_name in INJECTION_PATTERNS:
        if re.search(pattern, sanitized, re.IGNORECASE):
            matched.append(rule_name)
            risk = RiskLevel.HIGH
    # Stacked injection detection (multiple suspicious patterns)
    if len(matched) >= 3:
        risk = RiskLevel.CRITICAL
    is_safe = not matched  # heuristic result only; never authorization
    return ValidationResult(
        is_safe=is_safe,
        risk_level=risk,
        matched_rules=matched,
        sanitized_input=sanitized[:max_length] if is_safe else "",
    )

from functools import wraps
from typing import Callable
def input_guard(validator: Callable = validate_agent_input):
    """Decorator that guards agent entry points against unsafe input."""
    def decorator(func):
        @wraps(func)
        async def wrapper(user_input: str, *args, **kwargs):
            result = validator(user_input)
            if not result.is_safe:
                await log_security_event(
                    event="input_blocked",
                    risk=result.risk_level.value,
                    rules=result.matched_rules,
                    input_hash=hashlib.sha256(user_input.encode()).hexdigest(),
                )
                raise InputRejectedError(
                    f"Input blocked: matched {result.matched_rules}"
                )
            return await func(result.sanitized_input, *args, **kwargs)
        return wrapper
    return decorator
# Usage
@input_guard()
async def handle_user_message(message: str, session_id: str, **kwargs):
    """Process a validated user message through the agent."""
    flags = kwargs.get("_security_flags", [])
    if flags:
        # Route to sandboxed execution path
        return await agent.run_sandboxed(message, session_id)
    return await agent.run(message, session_id)

# docker-compose.agent-sandbox.yml
version: "3.8"
 
services:
  agent-sandbox:
    image: agent-tools:latest
    read_only: true
    security_opt:
      - no-new-privileges:true
      - seccomp:seccomp-profile.json
    cap_drop:
      - ALL
    tmpfs:
      - /tmp:size=64M,noexec,nosuid
    mem_limit: 512m
    cpus: "0.5"
    pids_limit: 64
    networks:
      - sandbox-net
    environment:
      - TOOL_TIMEOUT=30 # application must enforce this; env vars alone do nothing
      - MAX_OUTPUT_BYTES=65536
    volumes:
      - type: bind
        source: ./tool-workspace
        target: /workspace
        read_only: false
    dns:
      - 127.0.0.1           # Block external DNS by default
 
networks:
  sandbox-net:
    driver: bridge
    internal: true           # No external network access

# Install gVisor runsc runtime
curl -fsSL https://gvisor.dev/archive.key | sudo gpg --dearmor -o /usr/share/keyrings/gvisor-archive-keyring.gpg
echo "deb [signed-by=/usr/share/keyrings/gvisor-archive-keyring.gpg] https://storage.googleapis.com/gvisor/releases release main" | \
  sudo tee /etc/apt/sources.list.d/gvisor.list
sudo apt-get update && sudo apt-get install -y runsc
 
# Configure Docker to use gVisor
# Illustrative fragment only: merge into a backed-up daemon.json, validate,
# and schedule the disruptive Docker restart. Do not overwrite existing settings.
cat <<'EOF' > runsc-daemon-fragment.json
{
  "runtimes": {
    "runsc": {
      "path": "/usr/bin/runsc",
      "runtimeArgs": [
        "--network=none",
        "--directfs=false"
      ]
    }
  }
}
EOF
sudo systemctl restart docker
 
# Run agent sandbox with gVisor
docker run --runtime=runsc --rm --network=none --cap-drop=ALL --security-opt=no-new-privileges --user=65534:65534 \
  --read-only \
  --memory=512m \
  --cpus=0.5 \
  --pids-limit=64 \
  agent-tools:latest \
  python /tools/execute.py --tool="$TOOL_NAME" --args="$TOOL_ARGS"

from dataclasses import dataclass, field
@dataclass
class ToolPolicy:
    name: str
    allowed_args: dict[str, type]     # parameter name -> expected type
    max_calls_per_session: int = 10
    requires_approval: bool = False
    allowed_patterns: list[str] = field(default_factory=list)
    blocked_patterns: list[str] = field(default_factory=list)
TOOL_ALLOWLIST: dict[str, ToolPolicy] = {
    "read_file": ToolPolicy(
        name="read_file",
        allowed_args={"path": str},
        max_calls_per_session=20,
        allowed_patterns=[r"^/workspace/", r"^/data/public/"],
        blocked_patterns=[r"\.env$", r"\.key$", r"\.pem$", r"/etc/", r"/proc/"],
    ),
    "run_query": ToolPolicy(
        name="run_query",
        allowed_args={"sql": str, "database": str},
        max_calls_per_session=5,
        allowed_patterns=[r"^SELECT\s", r"^EXPLAIN\s"],
        blocked_patterns=[r"\bDROP\b", r"\bDELETE\b", r"\bUPDATE\b", r"\bINSERT\b", r"\bALTER\b"],
    ),
    "http_request": ToolPolicy(
        name="http_request",
        allowed_args={"url": str, "method": str},
        max_calls_per_session=10,
        requires_approval=True,
        allowed_patterns=[r"^https://api\.internal\."],
        blocked_patterns=[r"^https?://169\.254\.", r"^https?://metadata\.google\."],
    ),
    "execute_code": ToolPolicy(
        name="execute_code",
        allowed_args={"code": str, "language": str},
        max_calls_per_session=3,
        requires_approval=True,
        blocked_patterns=[r"import\s+subprocess", r"import\s+os", r"__import__", r"eval\(", r"exec\("],
    ),
}
class ToolGatekeeper:
    def __init__(self, allowlist: dict[str, ToolPolicy]):
        self.allowlist = allowlist
        self.call_counts: dict[str, int] = {}
    async def authorize(self, tool_name: str, args: dict) -> bool:
        if tool_name not in self.allowlist:
            await log_security_event(
                event="tool_denied_not_in_allowlist",
                tool=tool_name,
            )
            return False
        policy = self.allowlist[tool_name]
        # Check call count
        count = self.call_counts.get(tool_name, 0)
        if count >= policy.max_calls_per_session:
            await log_security_event(
                event="tool_denied_rate_limit",
                tool=tool_name,
                count=count,
            )
            return False