A Drupal recipe that installs a set of AI guardrails to protect public-facing AI interactions from two distinct categories of risk: structurally malicious input (injection attacks) and semantically harmful requests (topics with legal or reputational exposure). Apply this recipe as a baseline safety layer on any site where the AI module processes untrusted user input.
- Security coverage
-
Covered by the security team
- Maintenance
-
Actively maintained
- Development
-
Under active development
- Latest release
-
1.0.0
- Checked