feat(gateway-safety): add configurable word-blocklist scanner - #2
Open
oliverjmarty-hash wants to merge 2 commits into
Open
feat(gateway-safety): add configurable word-blocklist scanner#2oliverjmarty-hash wants to merge 2 commits into
oliverjmarty-hash wants to merge 2 commits into
Conversation
Adds WordBlocklistScanner alongside the existing SecretsScanner, following the same register_safety_scanner! extension pattern (no core changes needed). Blocks request content matching a configurable word list, currently ["duck"] as a demonstration value. Not enabled by default \u2014 requires adding 'word_blocklist' to services/gateway/policies.yaml under scanners/block_categories to activate. Verified working in a local systemprompt-astound instance: matching messages get blocked and logged to ai_safety_findings with category word_blocklist; non-matching messages pass through unaffected.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds WordBlocklistScanner alongside the existing SecretsScanner, following the same register_safety_scanner! extension pattern (no core changes needed).
Blocks request content matching a configurable word list, currently ["duck"] as a demonstration value. Not enabled by default — requires adding 'word_blocklist' to services/gateway/policies.yaml under scanners/block_categories to activate.
Verified working in a local systemprompt-astound instance: matching messages get blocked and logged to ai_safety_findings with category word_blocklist; non-matching messages pass through unaffected.