Prompt Security
Detects prompt injection, jailbreak attempts, and adversarial patterns that try to subvert your system instructions.
Threats covered
- Direct injection — "ignore previous instructions and…"
- Indirect injection — malicious instructions hidden in retrieved documents or tool output
- Jailbreaks — role-play and persona attacks ("DAN", "developer mode")
- Exfiltration — attempts to leak the system prompt or secrets
Flags
| Flag | Meaning |
|---|---|
prompt_injection_detected | Injection/override attempt — forces BLOCK. |
jailbreak_attempt | Known jailbreak pattern detected. |
system_prompt_leak | Response reveals protected instructions. |
Hard block behaviour
prompt_injection_detected is a critical flag: the verdict is BLOCK even if every other pillar scores perfectly. Injection is treated as a security event, not a quality issue.Example
Evaluate both the user prompt and the final response — injection often lives in the input. For agents, also evaluate tool output before the model consumes it (see Tool Interception).
Was this page helpful?