a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Review network segmentation and firewall/ACL design for security: zone separation, ruleset hygiene, lateral-movement containment, and zero-trust / microsegmentation. Use to assess or design network architecture defensively (not active testing).
$ npx -y skills add jassics/awesome-claude-security --skill network-segmentation-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/network-segmentation-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Review network segmentation and firewall/ACL design for security: zone separation, ruleset hygiene, lateral-movement containment, and zero-trust / microsegmentation. Use to assess or design network architecture defensively (not active testing).
name: network-segmentation-review description: >- Review network segmentation and firewall/ACL design for security: zone separation, ruleset hygiene, lateral-movement containment, and zero-trust / microsegmentation. Use to assess or design network architecture defensively (not active testing).
An assessment of how well the network limits blast radius: are zones separated, are firewall rules least-privilege, and is lateral movement contained — with prioritized fixes.
1. **Zoning & trust** — segmentation between internet/DMZ/internal/management/OT, per-environment (prod/dev) and per-tenant separation; where trust changes. 2. **Firewall / ACL hygiene** — overly broad rules (`any/any`), unused/shadowed rules, stale entries, missing egress filtering, default-allow. 3. **Lateral-movement containment** — is the internal network flat? Can one compromised host reach the whole estate? East-west controls, microsegmentation. 4. **Management & sensitive planes** — isolated management network, jump hosts, restricted access to admin interfaces, OT/ICS separation. 5. **Zero-trust posture** — identity-aware access vs. pure network location; explicit allow-listing.
1. Gather topology, firewall rulesets/ACLs, and zone definitions. 2. Assess against the areas above; flag broad/stale rules and flat segments. 3. Model the lateral-movement blast radius from a typical foothold. 4. Recommend segmentation, rule tightening (least privilege, default-deny egress), and management isolation, prioritized by blast-radius reduction.
A review: zone/rule · issue · severity · fix, plus a target segmentation design and egress policy. Visualize zones with `security-diagramming:architecture-diagram`; report with `security-reporting`.
Flat networks are the force-multiplier behind most breaches — containing east-west movement limits blast radius more than almost any other network control. Hunt broad (`any/any`) and stale firewall rules; default-deny egress is commonly missing and high-value. Pairs with `network-pentest` (which demonstrates the lateral paths).
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…