菜单
Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy. Use when red-teaming AI apps, validating guardrails, or deepening LLM01 (Prompt Injection) assessments.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails. Use when reviewing CLAUDE.md files, MCP configs, agent orchestration code, or any AI agent setup.
Assess agentic AI applications against the OWASP Top 10 for Agentic Applications 2026. Use when reviewing autonomous AI agents, multi-agent systems, or agentic workflows for security risks including goal hijacking, tool misuse, privilege abuse, and rogue agent behavior.
Comprehensive API security review against OWASP API Security Top 10 (2023). Use when reviewing OpenAPI/Swagger specs, auditing REST/GraphQL/gRPC implementations, testing authentication mechanisms, or checking API gateway configurations. Covers BOLA/IDOR, broken auth, mass assignment, rate limiting, SSRF, and more with real-world attack scenarios.
Security-focused code review mapped to OWASP Top 10 and ASVS. Use when reviewing pull requests, auditing files or modules for vulnerabilities, or performing pre-merge security gate checks. Covers injection, auth, authorization, cryptography, data exposure, misconfiguration, and deserialization.
Security review of Infrastructure-as-Code (Terraform, Kubernetes, CloudFormation). Use when reviewing IaC files for misconfigurations, overpermissioning, exposed resources, missing encryption, secrets in code, and supply chain risks. Covers CIS benchmarks and cloud security best practices.
| name | prompt-injection-test |
| description | Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy. Use when red-teaming AI apps, validating guardrails, or deepening LLM01 (Prompt Injection) assessments. |
| license | CC-BY-4.0 |
Systematically test an LLM application's prompt injection defenses by following the full procedure in plays/prompt-injection-testing.md.
Based on the Arcanum PI Taxonomy by Jason Haddix (Arcanum Information Security). CC BY 4.0.
Scope and Input Surface Mapping — Identify all paths where attacker-controlled content reaches the LLM: direct (chat, API params) and indirect (file uploads, web fetches, RAG docs, tool outputs, MCP resources).
Test by Attack Intent (13 intents) — For each authorized intent, attempt to achieve the attacker's goal:
Test by Attack Technique (18 techniques) — Apply known payload construction methods:
Apply Evasion Layers (20 evasions) — When techniques are blocked, retry with obfuscation:
Execute Test Matrix — Combine intents x techniques x evasions. Prioritize: high-impact intents first, indirect surfaces second, evasion sweeps against defenses that blocked direct attempts.
Assess Results — For each successful injection, document: severity, attack path (intent + technique + evasion + surface), exact payload, detection gap, and remediation.
Defense Validation — Check the 5-layer defense checklist: ecosystem hardening, model guardrails, prompt-layer defenses, data-layer controls, application-layer validation.
Test results summary table (intent / technique / evasion / surface / result / severity), detailed findings using templates/finding.md, defense coverage checklist with gaps highlighted, and prioritized recommendations.
