a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Turn a security topic into a structured mindmap — recon surface, an attack chain, a framework breakdown, or study notes. Use when organizing or explaining a topic radially rather than as a flow or report.
$ npx -y skills add jassics/awesome-claude-security --skill mindmap --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/mindmapContext preview
The summary Claude sees to decide when to auto-load this skill.
Turn a security topic into a structured mindmap — recon surface, an attack chain, a framework breakdown, or study notes. Use when organizing or explaining a topic radially rather than as a flow or report.
name: mindmap description: >- Turn a security topic into a structured mindmap — recon surface, an attack chain, a framework breakdown, or study notes. Use when organizing or explaining a topic radially rather than as a flow or report.
A hierarchical mindmap with a central topic and branching sub-topics, useful for recon surface maps, framework breakdowns (e.g. OWASP/ATT&CK), or learning notes.
1. Set the central node (the topic). 2. Add primary branches (the main categories), then sub-branches to a sensible depth (usually 2–3 levels). 3. Keep labels to a few words; lean on hierarchy, not sentences. 4. Render: prefer the Excalidraw MCP; otherwise emit a Mermaid `mindmap` block and an indented bullet outline as a fallback.
Good for kicking off OSINT (map the target's surface) or for `security-knowledge` study aids. For cause/effect or sequence, prefer `attack-tree` or an `architecture-diagram` instead.
A Claude Code plugin marketplace for the full cybersecurity & GenAI-security lifecycle — from recon and threat modeling to detection engineering, GRC, and CISO-level strategy. A pentester knows which OWASP test bends a broken-access-control endpoint.
Repo: jassics/awesome-claude-security
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Test the agent execution harness/runtime itself — LangChain/LangGraph, AutoGen, CrewAI, custom ReAct-style loops, or computer-use/browser-use agents — for…
Assess an autonomous / tool-using AI agent for security end-to-end: tool privileges, autonomy and approval boundaries, excessive agency, memory/state…
Test what an AI agent will actually do without human confirmation, including under injected-goal / prompt-injection scenarios, to validate its autonomy and…
Review the security of MCP (Model Context Protocol) servers/clients an agent uses: server trust tier, tool/resource description and result poisoning,…
Inventory the tools/functions an AI agent can call and audit their privileges, side effects, and approval requirements to find excessive-agency and…