a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Produce a board / executive security presentation — risk posture and direction, top risks in business terms, program progress against strategy, the metrics that matter, and investment asks tied to risk. Use to prepare for a board or leadership meeting. Audience is non-technical
$ npx -y skills add jassics/awesome-claude-security --skill board-deck --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/board-deckContext preview
The summary Claude sees to decide when to auto-load this skill.
Produce a board / executive security presentation — risk posture and direction, top risks in business terms, program progress against strategy, the metrics that matter, and investment asks tied to risk. Use to prepare for a board or leadership meeting. Audience is non-technical
name: board-deck description: >- Produce a board / executive security presentation — risk posture and direction, top risks in business terms, program progress against strategy, the metrics that matter, and investment asks tied to risk. Use to prepare for a board or leadership meeting. Audience is non-technical decision-makers.
A concise, decision-oriented deck that gives the board what they need: how exposed are we, are we improving, and what should they fund or decide — in business language.
1. **Bottom line** — overall risk posture and direction vs. last review (1 slide). 2. **Top risks** — 3–5 in business terms (loss scenarios, not CVEs), with severity and trend (`cyber-risk-quantification`). 3. **Program progress** — where the strategy stands vs. plan; key wins and what's behind (`security-strategy`). 4. **Metrics that matter** — a small, stable set (e.g. risk reduction, critical remediation %, MTTR, coverage, incident trend) — consistent across meetings so trend is readable. 5. **The ask** — investment/decisions needed, each tied to the risk it reduces and the consequence of inaction. 6. **Appendix** — supporting detail, incidents, benchmarks, regulatory items.
1. Confirm the audience and the **decision/ask** this meeting must produce — build backward from it. 2. Pull the risk picture (`cyber-risk-quantification`) and program status (`security-strategy`); translate to business language, drop jargon. 3. Keep it tight: one message per slide, few stable metrics, clear asks. 4. Generate the visuals (posture scorecard, risk heat map, trend) with `security-diagramming:infographic`; assemble narrative via `security-reporting:executive-summary`.
A board deck (slide outline + content + visual specs) plus a one-page executive summary. Render visuals with `security-diagramming`.
Boards optimize for decisions under uncertainty — lead with posture and the ask, not a tour of activity. Keep the metric set small and **stable** so trends are comparable meeting to meeting. Every ask ties to a risk and the cost of not acting.
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…