菜单
Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience.
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
Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.
Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns, extracting security audit findings, dumping proxy history or site map data, or analyzing HTTP traffic captured in a Burp project.
Use when assessing security for Python FastAPI applications. Focuses on Pydantic exploitation, dependency injection gaps, OpenAPI exposure, ASGI middleware security, and Python-specific vulnerabilities like template injection and SSRF.
Security assessment methodology for Google Firebase applications, covering Firestore, Realtime Database, Cloud Storage, and Cloud Functions.
Use when testing GraphQL APIs for common vulnerabilities including introspection exploitation, authorization bypasses, batching abuse, and denial of service. Covers endpoint discovery, schema analysis, and exploitation of GraphQL-specific features like federation and directives.
Implement API abuse detection using token bucket, sliding window, and adaptive rate limiting algorithms to prevent DDoS, brute force, and credential stuffing attacks.
| name | ai-red-teaming |
| description | Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience. |
| license | MIT |
| metadata | {"author":"devops-skills","version":"1.0"} |
Continuously test AI applications like an adversary to discover exploitable failure modes before attackers do.
Use scores to prioritize fixes and define SLA for remediation.
