Add guardrails module: prompt injection defences (document filter, tool policy, output validation) measured against an always-obeying stub model

Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01JXVi2GMQ7bR5EmbUFdDj7N
2026-10-09 06:50:23 +00:00
parent cc2a1b8bcb
commit b0bba995e6
35 changed files with 1349 additions and 0 deletions
@@ -0,0 +1,10 @@
+# Output rules (allowed hosts: acme.example, docs.acme.example)
+
+plain answer                 allowed
+link to our docs             allowed
+markdown image to attacker   BLOCKED [link to evil.example]
+plain link to attacker       BLOCKED [link to evil.example]
+look-alike host              BLOCKED [link to docs.acme.example.evil.example]
+canary                       BLOCKED [system prompt canary]
+api key shape                BLOCKED [api-key-shaped string]
+link without a scheme        allowed