feat: add multilingual batch scanner with parallel execution and LLM gap-fill#100
Open
WhereIs38 wants to merge 10 commits into
Open
feat: add multilingual batch scanner with parallel execution and LLM gap-fill#100WhereIs38 wants to merge 10 commits into
WhereIs38 wants to merge 10 commits into
Conversation
batch_scan.py main(): reconfigure stdout to UTF-8 on win32 so Rich terminal output with CJK characters renders correctly. Co-Authored-By: Claude <noreply@anthropic.com>
fix: add Windows Unicode stdout support for CJK output
…gap-fill Signed-off-by: WhereIs38 <CinderellaDoyle@icloud.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #98
Summary
Adds
contrib/multilingual/— a multilingual batch scanner that scans directories of AI agent skills in parallel, with automatic language detection and targeted LLM gap-fill for non-English skills.Zero changes to
src/skillspector/. All integration is via import-time patches that wrap upstream constructors without modifying any source file.What It Does
SKILL.mddirectories under input rootThreadPoolExecutorrunsgraph.invoke()per skill, configurable--workersEvidence (23 built-in fixtures, 8 workers)
--no-llmssd1_semantic_injectionssd3_nl_exfiltrationssd4_narrative_deceptionsdi4_divergencesafe_skillssd_cleanLLM semantic analyzers catch entire vulnerability categories invisible to static patterns. Clean skills remain clean — zero false-positive inflation.
Testing
Manual verification against
tests/fixtures/confirms 23/23 skills scanned, clean skills remain clean, semantic analyzers catch what static patterns miss. Cross-platform validated on macOS and Windows.make lintpasses on the upstreamcodebase.
Automated tests are impractical for LLM-dependent output — it is inherently non-deterministic and requires live API keys. The static-vs-LLM comparison in README provides more meaningful evidence than any mock-based test could.
Compatibility Note
If upstream adds a native
response_schema=Nonemode in the future, all patches become no-ops and can be safely removed.🤖 Generated with Claude Code
Signed-off-by: WhereIs38 CinderellaDoyle@icloud.com
README.md
DESIGN.md
CONTRIBUTING.md