스킬 rsi-skill
📦

rsi-skill

콘텐츠 리비전 r1 중간 위험 📁 파일 시스템 접근⚙️ 외부 명령어🌐 네트워크 접근🔑 환경 변수

Evaluate and Improve Prompts With Test Cases

Prompt changes can look useful without improving real results. This skill scores examples, proposes revisions, and retains candidates that improve training scores without lowering validation scores.

지원: Claude Codex Code(CC)
Maintain this Skill? Claim it 📊 72 적절함

내 에이전트로 설치

이 요청을 에이전트에 복사하세요. 공식 Skill 페이지와 매니페스트가 포함되어 있습니다.

에이전트 요청
Review the Skillstore skill "rsi-skill" from https://skillstore.io/skills/lambdasec-rsi-skill.md and its manifest at https://skillstore.io/api/skills/lambdasec-rsi-skill/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

에이전트는 계속해서 계획을 표시하고 보안 정책에서 요구하는 확인을 요청해야 합니다.

에이전트가 읽기 쉬운 리소스

AI 에이전트, 크롤러, 스크립트가 전체 페이지 대신 정리된 컨텍스트만 필요할 때 이 링크를 사용하세요.

테스트해 보기

"rsi-skill" 사용 중입니다. Summarize the documented GSM8K optimization example.

예상 결과:

  • The bundled example reports a baseline of 5/28 training cases and 2/12 validation cases.
  • The retained final revision reached 27/28 training cases and 11/12 validation cases.
  • Two intermediate revisions were discarded. These are documented results from one run, not guaranteed outcomes.

"rsi-skill" 사용 중입니다. Initialize a new sentiment classification task.

예상 결과:

  • Created a starter prompt for positive, negative, and neutral sentiment.
  • Added three labeled examples for editing.
  • This starter set is too small for validation splitting. Add representative cases before optimization.

보안 감사

중간 위험
v1 • 2026. 10. 28. 버전별 보고서 열기

Most static alerts concern harmless formatting, arithmetic examples, documentation links, or intended backend configuration. Four HTTP request findings expose credentials through unrestricted redirects; a separate model-grading weakness can undermine evaluation integrity. No evidence found of malicious instructions, embedded credentials, or intentional data theft.

6
스캔된 파일
520
분석된 줄 수
4
검토 항목
0
오탐 무시됨

확인된 보안 우려 사항 (1)

중간
Untrusted content can influence model-based grading
Judge mode concatenates task input and generated answers into a grading message. Attacker-controlled content can request PASS verdicts and undermine prompt selection.
The grader receives untrusted answer text without explicit data-only instructions and accepts a PASS prefix. Exploit success depends on the selected model.
기능 검토 항목 (4)

이 스킬에 대해 예상될 수 있는 실제 로컬 기능이므로 검토가 필요하지만, 확인된 악의적 동작으로는 집계되지 않습니다.

높음
Python HTTP libraries
req = urllib.request.Request(url, headers={"Authorization": f"Bearer {key}"} if key else {})
Authorization is attached as an ordinary request header before default urllib redirect handling. Cross-origin redirects can forward this bearer credential to another host.
높음
Python HTTP libraries
with urllib.request.urlopen(req, timeout=timeout) as r:
Default urlopen follows redirects without restricting the credential-bearing request to its original origin. A local redirect-handler check confirmed Authorization forwarding.
높음
Python HTTP libraries
req = urllib.request.Request(be["base"] + "/chat/completions", data=body, headers=headers)
The completion request includes Authorization in ordinary headers. A redirect accepted by urllib can send that credential to a different origin.
높음
Python HTTP libraries
with urllib.request.urlopen(req, timeout=300) as r:
The completion request uses default redirect handling without an origin check. Accepted redirects can carry the bearer credential to an unintended host.
감사자: codex
이 보고서 공유 및 인용

버전이 지정된 평가 보고서, 중립 배지, 임베드 카드 및 인용을 공유하세요. Skillstore는 근거를 보고하지만 이 Skill의 안전 여부를 판단하지 않습니다.

버전별 보고서 열기
보안 평가

보고서 링크 복사

https://skillstore.io/skills/lambdasec-rsi-skill/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 배지

[![Skillstore security assessment](https://skillstore.io/badges/skills/lambdasec-rsi-skill/security.svg)](https://skillstore.io/skills/lambdasec-rsi-skill?utm_source=security_passport_badge)

HTML 배지

<a href="https://skillstore.io/skills/lambdasec-rsi-skill?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/lambdasec-rsi-skill/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

임베드 카드

<iframe src="https://skillstore.io/embed/skills/lambdasec-rsi-skill.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
학술 인용 (APA · BibTeX · CFF)

APA 인용

lambdasec. (2026). rsi-skill security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/lambdasec-rsi-skill/audits/1

BibTeX 인용

@techreport{lambdasec-lambdasec-rsi-skill-2026, author = {lambdasec}, title = {rsi-skill security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/lambdasec-rsi-skill/audits/1}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "rsi-skill security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "lambdasec" date-released: "2026-10-28" url: "https://skillstore.io/skills/lambdasec-rsi-skill/audits/1" identifiers: - type: other value: "skillstore:lambdasec-rsi-skill:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore 점수

이 점수의 이유 증거 신뢰도: 중간
64
아키텍처
85
유지보수성
87
콘텐츠
65
커뮤니티
91
사양 준수

만들 수 있는 것

Refine classification instructions

Compare a classifier prompt against labeled examples and inspect failures before accepting a revision.

Compare reasoning prompts

Use the bundled math cases to compare prompt variants with numeric checks and a reproducible validation split.

Test agent instruction changes

Evaluate instruction text against representative cases and review the proposed changes before applying them.

이 프롬프트를 사용해 보세요

Create a first evaluation
Help me evaluate this prompt: [prompt]. Initialize a task directory and help me define expected answers. Confirm the backend before sending data.
Measure a baseline
Evaluate the prompt and cases in [directory] using [approved endpoint and model]. Report the baseline score, failed cases, and scoring methods without revising anything.
Run controlled optimization
Optimize [directory] for up to five rounds using [approved endpoint and model]. Keep the default validation split and copy rejection. Report scores and proposed changes.
Validate an instruction revision
Optimize [directory] using [evaluation model] and [proposal model] on [approved endpoint]. Reevaluate the best prompt on [independent test directory]. Review failures before requesting deployment approval.

모범 사례

  • Confirm the resolved endpoint and model before inference. Obtain approval for private remote data and avoid untrusted redirects.
  • Use representative cases and deterministic checks where possible. Reserve a separate final test set beyond the reused validation split.
  • Review failures and prompt changes, repeat evaluation, and obtain approval before replacing production instructions.

피하기

  • Sending confidential prompts or cases to an unapproved remote endpoint.
  • Treating validation gains from a small, repeatedly reused split as proof of general improvement.
  • Using model-judge verdicts as the only acceptance gate for adversarial or security-sensitive tasks.

자주 묻는 질문

Does this skill train model weights?
No. It revises instruction text and measures the resulting answers against test cases.
Which model services can it use?
It supports OpenAI-compatible chat endpoints, including OptiQ Cloud, local OptiQ servers, and explicitly configured services. API features vary by backend.
Can I keep evaluation data local?
Yes, with an approved local endpoint. Select it explicitly and verify backend resolution because cloud configuration takes priority over automatic local discovery.
How many cases should I provide?
The instructions recommend 10 to 40 representative cases. Fewer than six cases disable validation splitting.
How does it select a revision?
Training scores must improve, and validation scores must not decrease when a validation set exists. Complete copied test inputs are rejected by default.
Are improvements guaranteed and automatically deployed?
No. Results depend on the model, checks, and examples. The instructions require user approval before applying the saved best prompt.

개발자 세부 정보

작성자

lambdasec

라이선스

Apache-2.0

Skillstore 리비전

r1

버전 안내

작성자가 버전을 선언하지 않았습니다.

참조

87c9669baf85385959f9b0a344dc9dfc8d978f9c

유지보수 최신성

2026. 10. 28.

사용량

0 다운로드 · 0 조회

파일 구조

lambdasec의 다른 스킬

전체 보기
전체 보기