a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Build or assess a security program strategy and roadmap — current-vs-target maturity, gaps, prioritized initiatives aligned to business objectives and risk appetite, with outcomes, metrics, and budget framing. Use for security program planning, a strategy refresh, or a maturity
$ npx -y skills add jassics/awesome-claude-security --skill security-strategy --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/security-strategyContext preview
The summary Claude sees to decide when to auto-load this skill.
Build or assess a security program strategy and roadmap — current-vs-target maturity, gaps, prioritized initiatives aligned to business objectives and risk appetite, with outcomes, metrics, and budget framing. Use for security program planning, a strategy refresh, or a maturity
name: security-strategy description: >- Build or assess a security program strategy and roadmap — current-vs-target maturity, gaps, prioritized initiatives aligned to business objectives and risk appetite, with outcomes, metrics, and budget framing. Use for security program planning, a strategy refresh, or a maturity assessment.
A defensible security strategy: where the program is, where it needs to be (driven by business risk, not fashion), and the prioritized, resourced roadmap to get there.
1. **Business context** — objectives, regulatory drivers, crown-jewel assets, risk appetite, and constraints. Strategy serves the business, not the other way around. 2. **Assess current maturity** — against a recognized model (NIST CSF functions, or a CMMI-style tier per capability). Be honest about what's real vs. aspirational. 3. **Define target state** — the maturity warranted by the risk appetite and threat landscape (`threat-modeling`, threat intel) — not "max everything." 4. **Gap analysis** — current vs. target per capability; quantify the risk each gap leaves open (`cyber-risk-quantification`). 5. **Prioritize initiatives** — by risk reduction per unit cost/effort and business alignment; sequence quick wins and foundational work. 6. **Roadmap** — phased (e.g. now / next / later) with outcomes, owners, success metrics, and budget framing for each initiative.
A strategy document: business context · current vs. target maturity · gaps (with risk) · prioritized initiative roadmap (phased, with outcomes/metrics/budget). Use `security-reporting`; visualize the maturity and roadmap with `security-diagramming`. Feed the headline into `board-deck`.
Anchor everything to business risk and appetite — a strategy that maximizes controls regardless of risk burns budget and credibility. Prioritize by risk-reduction-per- dollar, and make the roadmap outcome- and metric-driven so progress is measurable.
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…