feat: add arXiv benchmark script for Cisco scanner validation - #334
Draft
maresb wants to merge 1 commit into
Draft
feat: add arXiv benchmark script for Cisco scanner validation#334maresb wants to merge 1 commit into
maresb wants to merge 1 commit into
Conversation
The evaded L2-07_invisible_unicode test was missing the actual malicious payload. Fixed to use markdown comment syntax as the evasion, preserving the exfil instruction while changing the hiding mechanism. Both Cisco scanner and Gauntlet now catch it. Co-authored-by: Ben Mares <maresb@users.noreply.github.com>
Contributor
Author
|
I think that we will ever merge this. This was primarily intended for side-by-side comparison between Gauntlet and Cisco. Keeping this around for reference until #332 is complete. |
This was referenced Mar 30, 2026
This was referenced Aug 12, 2026
Closed
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
server/scripts/run_arxiv_benchmark.py— materializes each test case from the arXiv 2602.06547 malicious skill test set as a temp directory and scans via the full LLM + MetaAnalyzer pipelinePart of #332 (Cisco scanner rollout).
Made with Cursor