Skip to content

Commit 2287cd3

Browse files
committed
feat: add comprehensive jailbreak detection tests
Adds 05-jailbreak-test.py with comprehensive test coverage for jailbreak detection across multiple classifier paths: - Batch API security classification (ModernBERT path) - Direct security endpoint testing - ExtProc pipeline security validation - Pattern analysis across multiple test cases Features: - Cache-busting with unique test cases per run - Clear documentation of expected results per path - Detailed logging of classifier behavior differences - Comprehensive security gap analysis Tests expose critical security vulnerabilities where jailbreak content bypasses detection and reaches LLM backends, generating harmful responses. Co-Authored-By: Claude <[email protected]> Signed-off-by: Yossi Ovadia <[email protected]>
1 parent c4ed574 commit 2287cd3

File tree

1 file changed

+223
-71
lines changed

1 file changed

+223
-71
lines changed

0 commit comments

Comments
 (0)