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 a cloud environment's security posture (AWS/Azure/GCP) across IAM, network, data protection, logging/monitoring, and workload configuration, mapped to CIS benchmarks, and produce ranked findings. Use for a CSPM-style assessment of an account/subscription/project you're
$ npx -y skills add jassics/awesome-claude-security --skill cloud-posture-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cloud-posture-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Review a cloud environment's security posture (AWS/Azure/GCP) across IAM, network, data protection, logging/monitoring, and workload configuration, mapped to CIS benchmarks, and produce ranked findings. Use for a CSPM-style assessment of an account/subscription/project you're
name: cloud-posture-review description: >- Review a cloud environment's security posture (AWS/Azure/GCP) across IAM, network, data protection, logging/monitoring, and workload configuration, mapped to CIS benchmarks, and produce ranked findings. Use for a CSPM-style assessment of an account/subscription/project you're authorized to review.
A posture assessment across the major control domains, each with findings, severity, and remediation, anchored to CIS Benchmarks / provider best practice.
1. **Identity & access** — IAM users/roles/policies, least privilege, MFA, root/ admin usage, key rotation, federation. (Deep dive: `cloud-iam-review`.) 2. **Network** — security groups/NSGs/firewall rules, public exposure, private connectivity, segmentation, egress controls. 3. **Data protection** — storage exposure, encryption at rest/in transit, key management, backups, public snapshots/buckets. 4. **Logging & monitoring** — audit logging (CloudTrail/Activity Log/Cloud Audit Logs), log integrity, alerting, guard/threat services enabled. 5. **Workload & service config** — compute hardening, managed-service settings, serverless permissions, secrets handling, metadata service (IMDSv2 etc.). 6. **Governance** — account/org structure, baseline guardrails (SCPs/Policies), tagging, drift.
1. Establish scope (accounts/subscriptions/projects, regions) and read access. 2. Walk each domain with `reference.md`; for identity use `cloud-iam-review`, for exposure quick-wins use `cloud-misconfig-scan`. 3. Record per finding: domain · control (CIS ref) · observation · severity · remediation. Use provider config/posture data, not assumptions. 4. Score (`security-reporting:cvss`) and rank; highlight internet-exposed and identity findings first.
A posture report grouped by domain with a CIS-mapped findings table + ranked top risks. Confirmed issues → `security-reporting:finding`; architecture via `security-diagramming:architecture-diagram`.
Most cloud breaches trace to **identity** over-permission and **public exposure** of data/compute — weight those. Map findings to CIS controls for traceability; verify against the current benchmark version for the provider.
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…