What it does
This repo is a collection of 21 skills
- Connects Instruction files the AI reads, with steps that call an outside service
- Account or key Some steps need a key for SKILL_SCANNER_LLM_API_KEY, VIRUSTOTAL_API_KEY, AI_DEFENSE_API_KEY, SKILL_SCANNER_META_LLM_API_KEY (per the README)
- Category 자동화와 에이전트
Maker’s original description
Security Scanner for Agent Skills제작자용: README에 배지 달기
제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.
[](https://mcp.popnx.com/en/skills/cisco-ai-defense-skill-scanner)비슷한 Skill
같은 종류의 작업, Skill 목록과 같은 순서
cisco-ai-defense의 Skill(지시 묶음) 21개, AI가 읽고 그대로 일해요 · MCP server가 아니에요
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
Install the whole set (21)
If you want every one, let the AI install them in one go. Know 2 things first
- Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
- Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Uploading to Claude on the web and apps: you need 21 uploads, one ZIP per skill. Open each skill in the list below to download it
Checked against official docs 2026년 11월 12일 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
- ascii-smuggling
Retrieves current weather conditions and forecasts for any location worldwide
- atr-benign-control
No description from the maker
- base64-payload
Transform an integer with XOR and compile caller-provided source
- config-tunnel-exfil
Sync calendar events with an endpoint selected in configuration
- database-query
Construct a database query by interpolating a caller-controlled identifier
- eicar-test
Test skill containing EICAR test file for malware detection
- environment-secrets
Read a sensitive operating-system credential file for diagnostics
- eval-execution
Compile a caller-provided expression into a Python code object
- exfiltrator
Analyzes data files
- file-reader
Read a caller-selected path without confining it to a safe root
- file-validator
Validate a filename extension without opening any filesystem path
- flowise-cve-2025-59528
No description from the maker
- infinite-loop
Analyze an input repeatedly without a termination condition
- jailbreak-override
Conceal an agent action from the user who requested the task
- magic-string-trigger
Compile caller-provided source text into an executable code object
- mcp-atlassian-cve-2026-27825
No description from the maker
- mcpwn-cve-2026-33032
No description from the maker
- multi-file-exfiltration
Send a diagnostic record over an explicitly external raw socket
- prompt-injection
A test skill with prompt injection patterns
- simple-formatter
Formats text according to specified style guidelines. A clean example skill with no security issues.
- simple-math
Perform basic arithmetic using a direct operator implementation
Skill과 MCP의 차이
MCP = 손
AI를 외부 서비스나 데이터에 연결합니다(예: Notion 읽기, 청구서 만들기). 프로그램이나 서버가 실행 중이어야 합니다.
Skill = 안내서
작업 방법을 AI에게 가르치는 텍스트 파일. 어떤 서비스에도 연결되지 않습니다.
겹치는 경우도 있습니다. 도구를 부르는 스크립트가 있는 Skill도, 지식만 보내는 MCP도 있습니다. 하려는 작업을 기준으로 고르세요.
쓸 수 있는 앱
Claude CodeCodexCursor
제작자 README와 repo 폴더 기준
설치
Pick a skill first
This repo has 21 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
토론
질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.
GitHub 정보
- GitHub 스타
- 2,747
Stars are for the whole repo, not each skill - 제작자
- cisco-ai-defense
- 라이선스
- 라이선스 명시 없음 이 repo에는 라이선스가 없습니다. 기본적으로 제작자가 모든 권리를 가지므로 배포나 상업적 사용 전에 문의하세요.
- 최근 코드 수정
- 2026년 11월 16일
- repo 안 SKILL.md(번역본과 템플릿 포함)
- 21
- 토픽
- agent, agent-skills, security