'ai-security' 검색 결과

This skill should be used when the user asks to "scan AI systems for security threats", "check for prompt injection vulnerabilities", "assess model security posture", "detect data poisoning risks", or "audit AI/ML pipeline security".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan security controls for LLM applications and AI agents, covering malicious instructions, data leakage, model tampering, and API access. Includes guidance and code examples for filtering outputs, enforcing permissions, isolating networks, and recording audit events.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing defenses against prompt injection in AI agents
• Filtering personal information from LLM responses
• Designing authentication and rate limits for LLM APIs

Monitor requests to an AI prediction API for signs of model copying or training-data exposure. Test an authorized model with simulated attacks, measure the risk, and evaluate defenses such as request limits and reduced prediction detail.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Monitoring a public or partner prediction API
• Measuring model copying risk before deployment
• Testing request limits and reduced prediction detail

Check training data and machine learning models for malicious changes, including backdoors that cause unexpected behavior on specific inputs. Combine data quality checks, model analysis, and file integrity verification, then document findings and retest after remediation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening third-party data before training
• Checking downloaded model weights before deployment
• Investigating unexpected behavior on specific inputs

Build a screening pipeline for web pages, PDFs, and images before an AI agent reads them. Extract hidden text, check for malicious instructions with detection models, and record decisions to block or allow content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening external content before an agent reads it
• Checking uploaded PDFs and images for hidden instructions
• Scanning documents before adding them to a knowledge base

Set up repeatable security tests for LLM apps with Promptfoo and DeepTeam. Connect them to automated build pipelines, detect renewed vulnerabilities to malicious instructions or data leakage, and compare results across model or prompt changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running automated attack tests on every code change
• Blocking merges when security tests fail
• Comparing security across model or prompt versions

Add checks to LLM prompts and responses using Llama Guard 3, NeMo Guardrails, and LLM Guard. Configure content screening, conversation boundaries, and sensitive-data filtering, then measure blocking and false-positive rates with labeled test prompts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding runtime safety checks to LLM, RAG, or agent apps
• Screening prompts for injection and jailbreak attempts
• Filtering sensitive or toxic model responses

Audit MCP servers, which provide external tools to AI agents, for hidden instructions, changes after approval, unsafe internal requests, and missing authentication. Use mcp-scan and manual checks to document risks and recommended fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing an MCP server before adding it to an agent
• Auditing an internally developed MCP server
• Checking approved tools for unexpected changes

Assess the security of RAG systems, which retrieve documents to support AI answers. Test whether stored vectors expose source text, leak documents between tenants, or allow inserted content to dominate search results, then document findings and controls.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assessing source-text exposure from stored vectors
• Checking data isolation between tenants
• Testing retrieval manipulation in a test collection

Assess security risks in AI systems by scanning prompts for known attack patterns and scoring data exposure, poisoning, and tool abuse risks. Map findings to MITRE ATLAS, an AI threat framework, and identify protective controls.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Scan application prompts for injection and jailbreak patterns
• Review malicious instructions in retrieved documents
• Assess training data exposure and poisoning risks

Analyze and apply AssemblyAI secret, region, consent, retention, deletion, and model-training controls. Use when reviewing security or regulated speech workflows. Trigger with "AssemblyAI security", "AssemblyAI privacy", or "data retention".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Harden AI/LLM deployments against prompt injection, data exfiltration, model theft, and supply chain attacks. Covers input validation, output filtering, access control, model API security, and compliance controls for production AI systems.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when attacking an AI/ML system or model — prompt injection & jailbreaks (Crescendo, Skeleton Key, Best-of-N), RAG/vector poisoning, agentic/MCP exploitation (CVE-2025-54136), ML supply-chain RCE (pickle CVE-2025-32434), model extraction / membership inference / adversarial suffixes (GCG)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Harden AI/LLM deployments against prompt injection, data exfiltration, model theft, and supply chain attacks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run autonomous AI-driven penetration tests on web applications using tools like Shannon, PentAGI, and similar frameworks. Use when tasks involve setting up automated penetration testing pipelines, combining AI agents with security tools (nmap, subfinder, nuclei, sqlmap), building autonomous exploit chains, generating pentest reports with proof-of-concept exploits, or integrating AI pentesting into CI/CD pipelines. Covers the full pentest lifecycle from reconnaissance to reporting using AI orchestration.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Hunt vulnerabilities in LLM-powered applications — direct/indirect prompt injection, system prompt extraction, ASCII smuggling, RCE via code tools, agentic AI exploits (ASI01-ASI10), data exfiltration via response channels, IDOR in chat history, jailbreak chains, RAG poisoning. Use when target has a chatbot, AI assistant, copilot, or agentic AI features.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AI-first security scanning with Medusa. 3,000+ detection patterns covering AI/ML, agents, MCP, RAG, prompt injection, and traditional SAST vulnerabilities. Wraps Medusa CLI with SARIF/JSON parsing, structured finding output, OWASP mapping, and remediation guidance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Test Retrieval-Augmented Generation (RAG) systems for data poisoning, prompt injection via retrieved documents, and data exfiltration through manipulated context windows. Use this skill when assessing RAG-based chatbots, knowledge bases, enterprise AI assistants, or any system that augments LLM responses with external document retrieval. Covers document injection, embedding manipulation, knowledge base poisoning, and cross-document inference attacks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Test Model Context Protocol (MCP) servers and tool-calling systems for security vulnerabilities including tool injection, parameter manipulation, privilege escalation, and data exfiltration through AI agent tool interfaces. Use this skill when assessing MCP server implementations, AI agent tool integrations, or any system that exposes tools to language models. Covers tool confusion attacks, cross-tool exploitation, and MCP server hardening assessment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Test Large Language Models for direct prompt injection vulnerabilities where user input overrides system instructions, extracts system prompts, bypasses safety filters, or causes unauthorized actions. Use this skill when assessing chatbots, AI assistants, LLM-powered tools, or any application that processes natural language input through an LLM. Covers role-playing attacks, instruction hierarchy exploitation, multi-turn manipulation, and context window abuse for comprehensive AI security testing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.