Skip to content

Add @ny-squared/guard to Tools – unified LLM security SDK#125

Open
nysquared-support-ux wants to merge 3 commits intocorca-ai:mainfrom
nysquared-support-ux:main
Open

Add @ny-squared/guard to Tools – unified LLM security SDK#125
nysquared-support-ux wants to merge 3 commits intocorca-ai:mainfrom
nysquared-support-ux:main

Conversation

@nysquared-support-ux
Copy link
Copy Markdown

@nysquared-support-ux nysquared-support-ux commented Apr 2, 2026

What is this?

Adds @ny-squared/guard to the Tools section.

Why it belongs here

  • One-liner protection: guard.wrap(new OpenAI()) intercepts every LLM call
    • OSS mode: rule-based detection, no API key, no network calls (Apache 2.0)
    • Pro mode: ML-enhanced cloud detection (~95% accuracy)
    • Scans for OWASP Top 10 LLM threats: prompt injection, jailbreaks, PII leakage, toxic content

Summary by CodeRabbit

  • 문서화
    • README 도구 목록에 ny-squared/guard 항목을 추가하고 SDK 설명(규칙 기반 OSS 모드 및 ML 기반 Pro 모드), OWASP Top10 위협 대응 내용 및 GitHub 별점 배지를 포함했습니다.

@coderabbitai
Copy link
Copy Markdown

coderabbitai bot commented Apr 2, 2026

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: e9ca6168-9150-4cc7-9367-2730f4952ed9

📥 Commits

Reviewing files that changed from the base of the PR and between 500dabc and f05512b.

📒 Files selected for processing (1)
  • README.md
✅ Files skipped from review due to trivial changes (1)
  • README.md

Walkthrough

README.md의 Tools 섹션에 @ny-squared/guard 항목(설명·GitHub 링크·스타 배지)이 한 줄 추가되었습니다.

Changes

Cohort / File(s) Summary
README 업데이트
README.md
Tools 섹션에 @ny-squared/guard 항목(설명, GitHub 링크, 스타 배지) 1줄 추가. 변경은 문서 추가만 포함하며 코드/공개 API 변경 없음.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

🚥 Pre-merge checks | ✅ 3
✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly and specifically describes the main change: adding the @ny-squared/guard package to the Tools section of the README, with a concise mention of its core value proposition as a unified LLM security SDK.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link
Copy Markdown

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🧹 Nitpick comments (2)
README.md (2)

121-121: 설명에서 다운로드 통계 언급을 제거하는 것을 고려하세요.

PR 설명에는 "254 npm downloads in the first week"가 언급되어 있지만, awesome 리스트에서는 일반적으로 홍보성 다운로드 수치보다는 기능적 특징에 집중합니다. 현재 README 설명은 이를 포함하지 않아 적절하지만, 향후 수정 시 다운로드 수치를 추가하지 않도록 주의하세요.

🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@README.md` at line 121, 요약: README의 항목 설명에서 홍보성 다운로드 통계("254 npm downloads in
the first week")를 제거하거나 추가하지 않도록 하세요; 수정 방법: awesome 목록에 있는 항목 설명인
"[`@ny-squared/guard`]" 텍스트를 검토해 다운로드 수치·홍보 문구를 삭제하고 대신 기능적 특징(예: "Unified LLM
Security SDK — one-liner protection for OpenAI/Anthropic/Gemini. Rule-based OSS
mode (Apache 2.0) + ML-enhanced Pro mode (~95% accuracy). Scans OWASP Top 10 LLM
threats.")만 남기며, 향후 커밋/PR에서 다운로드 통계가 포함되지 않도록 검토 기준에 명시하세요.

121-121: 일관성을 위해 GitHub 스타 배지를 추가하세요.

다른 대부분의 도구 항목에는 GitHub 스타 배지가 포함되어 있습니다(예: line 109-120). 일관성을 유지하기 위해 이 항목에도 배지를 추가하는 것을 고려하세요.

♻️ GitHub 스타 배지 추가 제안
-- [`@ny-squared/guard`](https://github.com/ny-squared/guard): Unified LLM Security SDK — one-liner protection for OpenAI/Anthropic/Gemini. Rule-based OSS mode (Apache 2.0) + ML-enhanced Pro mode (~95% accuracy). Scans OWASP Top 10 LLM threats.
+- [`@ny-squared/guard`](https://github.com/ny-squared/guard): Unified LLM Security SDK — one-liner protection for OpenAI/Anthropic/Gemini. Rule-based OSS mode (Apache 2.0) + ML-enhanced Pro mode (~95% accuracy). Scans OWASP Top 10 LLM threats. ![GitHub Repo stars](https://img.shields.io/github/stars/ny-squared/guard?style=social)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@README.md` at line 121, 요약: README의 항목 [`@ny-squared/guard`]에 다른 항목들처럼 GitHub
스타 배지를 추가하여 목록 형식을 일관되게 유지하세요; 수정 방법: README의 해당 리스트 항목(표시 텍스트
"@ny-squared/guard")을 찾아 링크 뒤에 GitHub 스타 배지(예: shields.io의
github/stars/ny-squared/guard 형태)를 삽입하고 다른 항목들(line 109-120과 동일한 배지 스타일/포맷)을 따라
배지 이미지와 링크 형식을 일관되게 적용하세요.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@README.md`:
- Line 121: The README entry for "@ny-squared/guard" contains a broken GitHub
link and an unsupported "~95% accuracy" claim; update the link to the correct
source (replace the non-existent "ny-squared/guard" URL with the package's npm
page or the actual repository) and either remove or qualify the accuracy claim
(e.g., change "~95% accuracy" to a sourced statement or add a citation to the
benchmark/README that supports it); reference the package identifier
"@ny-squared/guard", the release "v0.1.2", and the license "Apache-2.0" when
making the correction so reviewers can find the right project.

---

Nitpick comments:
In `@README.md`:
- Line 121: 요약: README의 항목 설명에서 홍보성 다운로드 통계("254 npm downloads in the first
week")를 제거하거나 추가하지 않도록 하세요; 수정 방법: awesome 목록에 있는 항목 설명인 "[`@ny-squared/guard`]"
텍스트를 검토해 다운로드 수치·홍보 문구를 삭제하고 대신 기능적 특징(예: "Unified LLM Security SDK — one-liner
protection for OpenAI/Anthropic/Gemini. Rule-based OSS mode (Apache 2.0) +
ML-enhanced Pro mode (~95% accuracy). Scans OWASP Top 10 LLM threats.")만 남기며, 향후
커밋/PR에서 다운로드 통계가 포함되지 않도록 검토 기준에 명시하세요.
- Line 121: 요약: README의 항목 [`@ny-squared/guard`]에 다른 항목들처럼 GitHub 스타 배지를 추가하여 목록
형식을 일관되게 유지하세요; 수정 방법: README의 해당 리스트 항목(표시 텍스트 "@ny-squared/guard")을 찾아 링크 뒤에
GitHub 스타 배지(예: shields.io의 github/stars/ny-squared/guard 형태)를 삽입하고 다른 항목들(line
109-120과 동일한 배지 스타일/포맷)을 따라 배지 이미지와 링크 형식을 일관되게 적용하세요.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 0c0a5618-78e1-4e5f-b5a5-64c8f59f98c0

📥 Commits

Reviewing files that changed from the base of the PR and between c8ae124 and 197871b.

📒 Files selected for processing (1)
  • README.md
📜 Review details
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2026-03-08T05:45:19.349Z
Learnt from: MaxwellCalkin
Repo: corca-ai/awesome-llm-security PR: 0
File: :0-0
Timestamp: 2026-03-08T05:45:19.349Z
Learning: The MaxwellCalkin/sentinel-ai repo uses compiled regex patterns (not ML inference) for LLM safety guardrails, achieving sub-millisecond latency. Its benchmark is fully self-curated (author designed both the regex patterns and the test cases), so 100% accuracy on that benchmark is expected by design. The ~20ms/~0.987 "Sentinel" figures are from Qualifire's unrelated "Sentinel" product, not this library.

Applied to files:

  • README.md

Copy link
Copy Markdown

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@README.md`:
- Line 12: 목차 항목 "[Awesome LLM Security ](`#awesome-llm-security-`)h"에 공백과 끝의 불필요한
'h' 및 끝나는 하이픈 때문에 앵커가 깨집니다; README의 해당 목차 항목(문자열 "[Awesome LLM Security
](`#awesome-llm-security-`)h")을 찾아 링크 텍스트 내 불필요한 공백을 제거하고 끝 하이픈과 'h'를 삭제해 올바른 앵커로
바꿉니다(예: "[Awesome LLM Security](`#awesome-llm-security`)").
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 02574418-ced8-4bb0-84dc-37dbe982012c

📥 Commits

Reviewing files that changed from the base of the PR and between 197871b and 500dabc.

📒 Files selected for processing (1)
  • README.md
📜 Review details
🧰 Additional context used
🪛 markdownlint-cli2 (0.22.0)
README.md

[warning] 12-12: Spaces inside link text

(MD039, no-space-in-links)

🔇 Additional comments (1)
README.md (1)

121-121: 도구 항목 업데이트 방향은 적절합니다.

Line 121은 이전 이슈였던 과장된 정확도 문구가 제거되어 있고, 링크/별 배지 포함 형태도 기존 Tools 섹션 스타일과 일관됩니다.

README.md Outdated
## Table of Contents

- [Awesome LLM Security ](#awesome-llm-security-)
- [Awesome LLM Security ](#awesome-llm-security-)h
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

목차 앵커가 깨져 있어 탐색이 오동작합니다.

Line 12에서 링크 뒤 h가 링크 외부로 남아 있고, 링크 텍스트 내부 공백도 있어 Markdown lint(MD039) 위반입니다. 목차 클릭 동작/가독성 모두 깨집니다.

🔧 제안 수정
-- [Awesome LLM Security ](`#awesome-llm-security-`)h
+- [Awesome LLM Security](`#awesome-llm-security-`)
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
- [Awesome LLM Security ](#awesome-llm-security-)h
- [Awesome LLM Security](`#awesome-llm-security-`)
🧰 Tools
🪛 markdownlint-cli2 (0.22.0)

[warning] 12-12: Spaces inside link text

(MD039, no-space-in-links)

🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@README.md` at line 12, 목차 항목 "[Awesome LLM Security
](`#awesome-llm-security-`)h"에 공백과 끝의 불필요한 'h' 및 끝나는 하이픈 때문에 앵커가 깨집니다; README의 해당
목차 항목(문자열 "[Awesome LLM Security ](`#awesome-llm-security-`)h")을 찾아 링크 텍스트 내 불필요한
공백을 제거하고 끝 하이픈과 'h'를 삭제해 올바른 앵커로 바꿉니다(예: "[Awesome LLM
Security](`#awesome-llm-security`)").

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant