Files
bot-bottle/tests/unit
didericis-claude abcb336e7c
lint / lint (push) Failing after 1m24s
test / unit (pull_request) Successful in 30s
test / integration (pull_request) Successful in 44s
fix(dlp): rework naive injection to proximity-based disclosure+jailbreak
Token detection is already handled by the token_patterns detector
running separately — calling it again from scan_naive_injection was
redundant. New logic:

- Warn on any disclosure phrase
- Warn on any jailbreak phrase
- Block when both appear within 500 chars of each other

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-05 20:34:21 +00:00
..