127 件 ・ 関連度順
概要と使いどころ
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.
日本語の概要は準備中です。原文の説明を表示しています。
Security audit and vulnerability scanning for AI agent skills before install. Detects prompt injection, dangerous code, exfiltration, credential harvesting, and supply chain risks. Use when evaluating untrusted skills or gating installs.
日本語の概要は準備中です。原文の説明を表示しています。
Audit an AI agent skill before installing it. Use proactively whenever the user is about to add, install, enable, or evaluate an unfamiliar skill — including phrases like "audit this skill", "is this skill safe", "scan skill before install", "check skill for malicious code", "review this plugin", or any pre-install gate on an untrusted, third-party, or community-distributed skill bundle. Runs ten categories of static checks (code execution, network exfiltration, credential harvesting, persistence, prompt injection, supply-chain hooks, obfuscation, destructive filesystem ops, secrets, Trojan Source / homoglyphs) and emits a PASS / WARN / FAIL verdict.
日本語の概要は準備中です。原文の説明を表示しています。
Audits legal AI skills, prompts, workflows, MCP/tool instructions, and agent packages for prompt injection, malicious instructions, unsafe scripts, suspicious metadata, credential exposure, exfiltration paths, persistence mechanisms, and supply-chain risk. Use before installing, importing, publishing, promoting, modifying, or trusting third-party or generated AI skills and legal workflows. Do not use as a generic code review unless skill trust, workflow safety, prompt injection, or supply-chain hygiene is in scope.
日本語の概要は準備中です。原文の説明を表示しています。
Elite incident response and legal compliance guidance for data breaches under GDPR Articles 33 & 34. Use when: (1) User reports a data breach or security incident — including "is this even a personal data breach?" triage, (2) User asks about breach notification obligations or deadlines, (3) User mentions "72 hours", Art. 33, Art. 34, or notification requirements, (4) Discussion involves security incidents affecting personal data, (5) User needs breach risk assessment using ENISA methodology, (6) User mentions "Data Breach" or "Incident" or "Data Leakage" or "Ransomware" or "Exfiltration", (7) User needs to determine Controller vs Processor obligations, (8) Cross-border breach scenarios requiring Lead SA determination, (9) User needs a mitigation playbook or immediate response recommendations, (10) User needs audit-ready breach documentation (.docx) or an EDPB-template-aligned breach notification / evidence file — including follow-up and withdrawal notifications, (11) Breach involves an AI system requiring AI Act Art. 73 serious incident screening.
日本語の概要は準備中です。原文の説明を表示しています。
Learn from public breach disclosures — extract the audit question each one implies and check your own stack. Capital One IMDS abuse, LastPass vault exfiltration, Okta Lapsus$, Snowflake credential reuse, MOVEit, SolarWinds, Equifax, Target POS, Codecov, Uber, Twilio — what would you check now if your boss said 'could that happen to us?' Use when the user mentions 'breach analysis,' 'lessons learned,' 'security postmortem,' 'breach patterns,' 'breach lessons,' 'has this happened to us,' 'apply breach lessons,' 'preempt breaches,' 'security retrospective,' 'real-world security incidents,' or wants to harden against known attacker playbooks.
日本語の概要は準備中です。原文の説明を表示しています。
Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience.
日本語の概要は準備中です。原文の説明を表示しています。
Harden AI/LLM deployments against prompt injection, data exfiltration, model theft, and supply chain attacks.
日本語の概要は準備中です。原文の説明を表示しています。
Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.
日本語の概要は準備中です。原文の説明を表示しています。
Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.
日本語の概要は準備中です。原文の説明を表示しています。
Think and work like an expert Building Science Engineer. Use when a task calls for Building Science Engineer judgment. Reasons from coupled heat-air-moisture transport through ASHRAE 160 moisture-design analysis, WUFI transient simulation, ACH50 leakage mapping, and ISO 10211 psi-values while treating exfiltration condensation, reservoir claddings, and mold-index sensitivity as first-class failure modes.
日本語の概要は準備中です。原文の説明を表示しています。
Test AI/LLM features that ship in your product. Covers prompt regression testing, response quality evaluation, tool-call validation, hallucination and RAG grounding checks, nondeterministic-output strategies, red-team/safety scans, eval frameworks, and agent-as-target injection (indirect injection via tool output / RAG / scan reports, self-propagating payloads, data exfiltration via an agent) plus a bundled detector for untrusted content. Use when: "test our LLM feature," "prompt regression test," "eval framework," "hallucination test," "RAG grounding," "nondeterministic output," "AI feature testing," "red-team our chatbot," "indirect prompt injection," "agent reading untrusted tool output," "production AI quality." Not for: using AI to generate your own test code — use ai-test-generation. Not for: classifying CI failures with AI — use ai-bug-triage. Not for: EU AI Act / GDPR conformity of an AI feature — use compliance-testing. Not for: canary/flag rollout of an AI feature — use testing-in-production. Related: ai-test-generation, ai-qa-review, api-testing, compliance-testing, security-testing, risk-based-testing, test-data-management.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guide for defending AI applications against prompt injection, jailbreak attacks, indirect injection via tool outputs, and data exfiltration through tool calls — input sanitization, output filtering, canary token detection, and layered defense architecture / Panduan ahli pertahanan aplikasi AI terhadap prompt injection, serangan jailbreak, injeksi tidak langsung via output tool, dan eksfiltrasi data melalui tool calls — sanitasi input, filtering output, deteksi canary token, dan arsitektur pertahanan berlapis.
日本語の概要は準備中です。原文の説明を表示しています。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption, or secret exposure caused by an agent chain. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
日本語の概要は準備中です。原文の説明を表示しています。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for enterprise mail abuse, OAuth consent, inbox or forwarding rules, transport rules, shared mailbox access, phishing chains, and token-to-mailbox side effects. Use when the user asks to trace mailbox rules, OAuth consent grants, forwarding or delegate abuse, shared mailbox access, message-trace evidence, or explain how mail artifacts turn into persistence, exfiltration, or privilege. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
日本語の概要は準備中です。原文の説明を表示しています。
Put an inline firewall and containment layer in front of agent network traffic, tool calls, and MCP traffic before you trust an agent with local secrets.
日本語の概要は準備中です。原文の説明を表示しています。
Automated security scanner for external skill/agent content fetched from GitHub or web sources. Runs a 7-step PASS/FAIL security gate against fetched markdown/text content.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
Use when building autonomous LLM agents operating in live environments. Protects against prompt injection, tool abuse, data exfiltration, and runaway loops. Keywords: guardrails, prompt injection, IPI, safety, sandboxing, NeMo, LLM Guard.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
LLM prompt injection playbook. Use when testing AI/LLM applications for direct injection, indirect injection via RAG/browsing, tool abuse, data exfiltration, MCP security risks, and defense bypass techniques.
日本語の概要は準備中です。原文の説明を表示しています。
Identify and exploit GraphQL API vulnerabilities by leveraging Introspection queries to dump the entire database schema, performing query batching to bypass rate limits (brute forcing), and extracting deeply nested unauthorized data via graph relationship abuse.
日本語の概要は準備中です。原文の説明を表示しています。
Identify and exploit Cross-Origin Resource Sharing (CORS) misconfigurations. Use this skill when auditing APIs or web applications that share sensitive data across domains, forcing victims' browsers to inadvertently leak private information (e.g., API keys, PII, CSRF tokens) to an attacker-controlled website.
日本語の概要は準備中です。原文の説明を表示しています。
Hunts for unusual outbound network connections by flagging direct-to-IP traffic, uncommon ports, rare destinations, high data-egress ratios, and connections from unexpected processes in network telemetry. Activates for requests to hunt unusual outbound traffic, detect suspicious egress, or find anomalous external connections.
日本語の概要は準備中です。原文の説明を表示しています。