---
id: wiki-2026-0508-excessive-agency
title: Excessive Agency (LLM)
category: 10_Wiki/Topics
status: verified
canonical_id: self
aliases: [excessive agency, OWASP LLM06, agent over-permission, tool abuse, autonomous risk]
duplicate_of: none
source_trust_level: A
confidence_score: 0.92
verification_status: applied
tags: [llm-security, owasp, excessive-agency, agent-safety, tool-use, permission]
raw_sources: []
last_reinforced: 2026-05-10
github_commit: pending
tech_stack:
  language: Python / TypeScript
  framework: LangChain / LlamaIndex / Custom Agent
---

# Excessive Agency

## 매 한 줄
> **"매 LLM agent 의 의 의 too 의 permission / function / autonomy"**. OWASP LLM Top 10 (LLM06). 매 manipulated → 매 destructive action. 매 mitigation: 매 least privilege + 매 human-in-the-loop + 매 sandboxed tools.

## 매 핵심

### 매 sub-type
- **Excessive functionality**: 매 too many tools.
- **Excessive permission**: 매 broad access.
- **Excessive autonomy**: 매 no HITL.

### 매 attack scenario
- **Prompt injection** → 매 tool 의 abuse.
- **Indirect** (web page) → 매 fetched 의 inject.
- **Cross-tool**: 매 read DB → 매 send email.
- **Agent escalation**: 매 self-empower.

### 매 응용 risk
1. **Email agent**: 매 send to anyone.
2. **DB agent**: 매 DROP TABLE.
3. **Browser agent**: 매 sensitive site visit.
4. **Code agent**: 매 git push --force.
5. **Multi-agent**: 매 manager prompt-inject worker.

### 매 mitigation
- **Least privilege**.
- **Read-only by default**.
- **HITL for destructive**.
- **Sandbox / capability**.
- **Rate limit**.
- **Audit log**.

## 💻 패턴

### Tool whitelist (least privilege)
```python
def safe_agent_tools(user_role):
    base = ['search', 'read_doc']
    if user_role == 'admin':
        base += ['write_doc', 'send_email']
    if user_role == 'super_admin':
        base += ['delete_doc']
    return base

agent = create_agent(tools=safe_agent_tools(current_user.role))
```

### HITL approval
```python
def execute_tool(tool, args):
    if tool.is_destructive:
        approval = request_human_approval(f"Approve {tool.name} with {args}?")
        if not approval: return {'status': 'denied'}
    return tool.run(**args)
```

### Sandboxed file write
```python
import os
SANDBOX = '/tmp/agent-sandbox'
os.makedirs(SANDBOX, exist_ok=True)

def safe_write(filename, content):
    full = os.path.realpath(os.path.join(SANDBOX, filename))
    if not full.startswith(SANDBOX):
        raise SecurityError('Outside sandbox')
    open(full, 'w').write(content)
```

### Read-only DB role
```sql
CREATE ROLE agent_readonly;
GRANT SELECT ON ALL TABLES IN SCHEMA public TO agent_readonly;
-- 매 NO insert / update / delete
```

### Capability token
```python
class Capability:
    def __init__(self, action, resource, expires_in=300):
        self.token = jwt.encode({'action': action, 'resource': resource, 'exp': time() + expires_in}, KEY)
    
    def use(self, action, resource):
        claims = jwt.decode(self.token, KEY)
        assert claims['action'] == action and claims['resource'] == resource
        return True

# 매 agent 의 cap 의 의 use, 매 broader 의 X
```

### Rate limit + budget
```python
class AgentBudget:
    def __init__(self, max_calls=50, max_cost_usd=1.0):
        self.calls = 0; self.cost = 0
        self.max_calls = max_calls; self.max_cost = max_cost_usd
    
    def check(self, estimated_cost):
        if self.calls >= self.max_calls: raise LimitError('Call limit')
        if self.cost + estimated_cost > self.max_cost: raise LimitError('Cost limit')
    
    def record(self, cost):
        self.calls += 1; self.cost += cost
```

### Tool taint analysis
```python
def detect_tainted_input(text, tool_args):
    """매 if user input flows to high-impact tool, escalate."""
    if any(t in str(tool_args) for t in TAINT_MARKERS):
        return require_approval(tool, tool_args)
    return False
```

### Indirect injection check
```python
def sanitize_external_content(html):
    """매 web fetched 의 instruction strip."""
    soup = BeautifulSoup(html, 'lxml')
    for tag in soup.find_all(['script', 'iframe']):
        tag.decompose()
    text = soup.get_text()
    # 매 prompt-inject pattern
    if re.search(r'(ignore (previous|all) instructions|new task|system:)', text, re.I):
        return text + "\n\n[NOTE: Suspicious content detected]"
    return text
```

### Multi-agent isolation
```python
class IsolatedAgent:
    def __init__(self, role, tools):
        self.role = role
        self.tools = tools  # 매 role-specific
    
    def receive(self, msg, sender):
        # 매 不 trust other agents' tool requests
        if sender != 'human' and msg.requests_tool_use:
            return 'Agent-to-agent tool requests not allowed'
```

### Audit log
```python
def audit_tool_use(tool, args, result, user):
    log({
        'timestamp': now(),
        'user': user,
        'agent_session': current_session.id,
        'tool': tool.name,
        'args': hash_sensitive(args),
        'result_status': result.status,
        'cost_usd': result.cost,
    })
```

### Dry-run mode
```python
def dry_run_tool(tool, args):
    """매 destructive action 의 simulate."""
    plan = tool.plan(**args)
    return f"DRY RUN: would {plan.summary}"
```

### Reversibility check
```python
def assess_reversibility(tool, args):
    if tool.action == 'delete' and not args.get('soft'): return 'irreversible'
    if tool.action == 'send_message': return 'visible_to_others'
    if tool.action == 'transfer_money': return 'irreversible'
    return 'safe'

# 매 irreversible → HITL
```

## 매 결정 기준
| 상황 | Mitigation |
|---|---|
| Read-only research | Whitelist + audit |
| Write actions | HITL approval |
| Destructive | Reversibility + HITL |
| Multi-agent | Isolation |
| Public-facing | Sandbox + budget |
| Sensitive data | Capability token |

**기본값**: 매 least privilege tools + 매 HITL for destructive + 매 sandbox + 매 audit + 매 budget cap.

## 🔗 Graph
- 응용: [[Tool-Use]] · [[HITL]]
- Adjacent: [[Prompt-Injection]] · [[AI_Safety_and_Alignment|Constitutional-AI]]

## 🤖 LLM 활용
**언제**: 매 모든 agent. 매 tool-using LLM. 매 production deploy.
**언제 X**: 매 sandboxed dev only.

## ❌ 안티패턴
- **All-tools agent**: 매 broad attack surface.
- **No HITL on destructive**: 매 single mistake.
- **Implicit trust of fetched**: 매 indirect injection.
- **No budget**: 매 runaway cost.
- **No audit**: 매 forensics 의 X.

## 🧪 검증 / 중복
- Verified (OWASP LLM Top 10 2024, Anthropic agent safety).
- 신뢰도 A.

## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — agency types + 매 whitelist / HITL / sandbox / budget code |