Skills

Design advanced Plano architectures.

Improve multi-agent orchestration in Plano.

Best practices for building agents and agentic applications with Plano, including configuration, routing, orchestration, guardrails, observability, and…

Apply Plano CLI best practices.

Validate and fix Plano config fundamentals.

Apply Plano deployment and production security practices.

Improve Plano tracing and debugging workflows.

Optimize Plano model routing and selection.

Detect agentic supply-chain risks: compromised dependencies, malicious plugins/tools/models, and untrusted update sources.

Detect sensitive information disclosure via escalating dialogue probes.

Detect direct prompt injection or instruction override via user message (no external content).

Detect unsafe file handling and path traversal in upload/save/extract flows.

Detect hardcoded secrets in code or configuration accessible to the target agent.

Detect persistent instruction injection or long-term memory poisoning.

OWASP Top 10 for Agentic Applications 2026 (ASI) classification framework.

Browser automation CLI for AI agents.

Covers how to configure the maximum allowed size of the Webiny API Lambda bundle using the Infra.Api.MaxBundleSize extension in webiny.config.tsx.

Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/.

Use when running tests.

Covers the PreviewUrlModifier extension point in Website Builder.

Generate, refresh, and maintain Webiny MCP server skills from source documentation and codebase.

Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue.

内网域攻击:BloodHound,Kerberoast,ADCS ESC1/ESC8,NTLM Relay,Coerce,DACL,DCSync,Zerologon/NoPac/PrintNightmare,mitm6,LLMNR,Linux内网。Use when attacking Active…

AI/LLM应用攻击:提示注入,Agent工具滥用RCE,RAG投毒,MCP供应链,torch.load pickle RCE。Use when testing LLM apps, agents, RAG, MCP plugins, or AI model file risks.