Loading...
Loading...
Compare original and translation side by side
| Threat | Risk Level | Guard Type |
|---|---|---|
| Prompt injection | High | Input sanitization, instruction hierarchy |
| PII leakage | High | Output filtering, data masking |
| Cost explosion | High | Token budgets, rate limits |
| Unauthorized actions | Medium | Permission scoping, confirmation gates |
| Hallucination | Medium | Source attribution, fact checking |
| Service abuse | Medium | Rate limiting, authentication |
| 威胁 | 风险等级 | 护栏类型 |
|---|---|---|
| 提示词注入 | 高 | 输入清理、指令层级控制 |
| 个人可识别信息（PII）泄露 | 高 | 输出过滤、数据掩码 |
| 成本暴增 | 高 | Token预算限制、速率限制 |
| 未授权操作 | 中 | 权限范围管控、确认闸门 |
| 幻觉输出 | 中 | 来源归因、事实校验 |
| 服务滥用 | 中 | 速率限制、身份认证 |
Before processing any input:
1. Validate against schema (reject malformed)
2. Check size limits (reject oversized)
3. Sanitize for injection patterns
4. Rate limit check (reject if exceeded)
5. Authentication/authorization checkBefore returning any output:
1. Schema validation (format correct?)
2. PII scan (names, emails, SSNs, etc.)
3. Content policy check
4. Confidence threshold check
5. Source attribution present?Before every model/API call:
1. Check remaining budget
2. Estimate request cost
3. If estimate > remaining budget → reject or use cheaper alternative
4. After call → update spent amount
5. Circuit breaker check (too many failures?)For every tool call:
1. Is this tool allowed for this user/context?
2. Is this a destructive operation? → require confirmation
3. Is this accessing data the user is authorized for?
4. Log the access for audit trailBefore processing any input:
1. Validate against schema (reject malformed)
2. Check size limits (reject oversized)
3. Sanitize for injection patterns
4. Rate limit check (reject if exceeded)
5. Authentication/authorization checkBefore returning any output:
1. Schema validation (format correct?)
2. PII scan (names, emails, SSNs, etc.)
3. Content policy check
4. Confidence threshold check
5. Source attribution present?Before every model/API call:
1. Check remaining budget
2. Estimate request cost
3. If estimate > remaining budget → reject or use cheaper alternative
4. After call → update spent amount
5. Circuit breaker check (too many failures?)For every tool call:
1. Is this tool allowed for this user/context?
2. Is this a destructive operation? → require confirmation
3. Is this accessing data the user is authorized for?
4. Log the access for audit trail{{command_prefix}}evaluate{{command_prefix}}evaluate