Bryan Frimin ef8402ca93 Add reusable agent guardrails for prompt injection and data leaks ...

Introduce a pkg/agent/guardrail package with three guardrails that
can be composed into any agent:

- PromptInjectionGuardrail: LLM-based input classifier that detects
  prompt injection attempts before the agent processes them.
- SensitiveDataGuardrail: pattern-based output check for leaked
  tokens, keys, connection strings, and raw SQL.
- SystemPromptLeakGuardrail: configurable output check that detects
  system prompt content in responses using caller-provided
  fingerprints.

The classifier prompt is embedded from a plain text file for easy
review and editing.

Signed-off-by: Bryan Frimin <bryan@getprobo.com>

2026-03-30 14:18:29 +02:00

2.0 KiB

Raw Permalink Blame History

View Raw