a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Assess the security risk of a technology or product decision for leadership — new technology/vendor adoption, build-vs-buy, third-party/supply-chain, or M&A technical due diligence — and give a clear recommendation with trade-offs. Use to inform a strategic technology decision.
$ npx -y skills add jassics/awesome-claude-security --skill tech-risk-assessment --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/tech-risk-assessmentContext preview
The summary Claude sees to decide when to auto-load this skill.
Assess the security risk of a technology or product decision for leadership — new technology/vendor adoption, build-vs-buy, third-party/supply-chain, or M&A technical due diligence — and give a clear recommendation with trade-offs. Use to inform a strategic technology decision.
name: tech-risk-assessment description: >- Assess the security risk of a technology or product decision for leadership — new technology/vendor adoption, build-vs-buy, third-party/supply-chain, or M&A technical due diligence — and give a clear recommendation with trade-offs. Use to inform a strategic technology decision.
A decision-ready security risk assessment of the option(s) under consideration, with a recommendation that weighs security against velocity, cost, and strategic fit.
1. **Frame the decision** — what's being decided (adopt X / build vs. buy / acquire Y), the options, the data/systems involved, and the decision criteria. 2. **Assess each option's security posture:**
handling and residency, integration and access scope, lock-in, and exit.
radius if the vendor/component is compromised.
compliance exposure, and integration risk. 3. **Assess integration & data risk** — trust boundaries created, data exposure, identity/access, and the new attack surface (`threat-modeling`). 4. **Total cost incl. security** — build/operate/secure cost over time, not just license/sticker. 5. **Recommend** — a clear call with the risk trade-offs, required conditions/ mitigations, and residual risk stated honestly.
A tech-risk assessment: decision · options · per-option security posture · third- party/integration/data risk · total cost incl. security · recommendation + conditions
`security-diagramming`.
Decide with explicit trade-offs, not security absolutism — the goal is the best risk-adjusted technology choice for the business. Weight third-party/supply-chain and exit/lock-in risk; they're routinely underestimated. State residual risk and the conditions under which the recommendation holds.
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…