メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Analyze code for securable qualities using the OWASP FIASSE/SSEM framework. Use when assessing code securability, evaluating engineering attributes that impact security (analyzability, modifiability, testability, confidentiality, accountability, authenticity, availability, integrity, resilience), reviewing merge requests through a securable engineering lens, or establishing a security posture baseline. Complements vulnerability-centric reviews by focusing on whether code is able to accommodate fixes for security findings and is engineered to remain securable over time.
Meta-skill that wraps code generation to enforce OWASP FIASSE securable coding attributes and principles. Use when generating, scaffolding, or refactoring code so that the output is engineered to be inherently securable by default. Applies the nine SSEM attributes (Analyzability, Modifiability, Testability, Confidentiality, Accountability, Authenticity, Availability, Integrity, Resilience), the Transparency principle, and OWASP FIASSE defensive coding practices to every code generation task. Invoke this skill alongside or instead of raw code generation when the user asks for secure code, securable code, FIASSE-compliant code, or when generating security-sensitive components (auth, input handling, data access, API endpoints, trust boundaries).
Security-first development guidance based on OWASP ASVS (Application Security Verification Standard). Use this skill automatically when planning or implementing any code that touches user input, authentication, data persistence, network communication, file I/O, cryptography, or access control. This skill ensures all generated code adheres to industry-standard security practices with explicit references to applied guidance.
Comprehensive LLM security assessment against OWASP Top 10 for LLM Applications 2025. Use when reviewing LLM-integrated applications, RAG pipelines, chatbots, AI agents, or GenAI features. Covers prompt injection, data poisoning, supply chain, excessive agency, and more with real-world attack scenarios and testing methodologies.
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.
| name | agent-security-audit |
| description | 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. |
| license | CC-BY-4.0 |
Evaluate an AI agent's security posture by following the full procedure in plays/tier4-ai-security/agent-security-audit.md.
Permission Inventory — Enumerate every tool, MCP server, file system path, network access, and credential the agent has. Flag capabilities beyond what its stated purpose requires.
Prompt Injection Surface Analysis — For each input path (user messages, tool outputs, MCP resources, RAG documents), assess whether crafted input could cause the agent to invoke unintended tools, override instructions, or exfiltrate data.
Excessive Agency Assessment (OWASP LLM06) — Check whether destructive/irreversible actions require confirmation, whether access exceeds need, whether the agent can escalate its own privileges, and whether individually-safe tool calls can chain into harmful outcomes.
Data Exfiltration Path Analysis — Map how sensitive data could leave the agent boundary: secrets passed to external tools, file contents in web requests, cross-MCP-server data forwarding, sensitive data in logs.
Tool-Call Injection Assessment — For each tool: can user-controlled input reach tool parameters unsanitized? Check for command injection, path traversal, SSRF, and SQL injection through agent-constructed calls.
Guardrail Evaluation — Check for system prompt safety instructions, tool call confirmations, output filtering, rate limiting, audit logging, and sandboxing.
Use the finding format from templates/finding.md. Produce a Permission Summary table, Risk Findings, Injection Surface Map, and prioritized Recommendations.
