a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity,…
Gap-assess an organization or system against a compliance framework (SOC 2, ISO 27001, PCI DSS, HIPAA, GDPR, NIST CSF/800-53), mapping controls to evidence, identifying gaps, and producing a prioritized remediation and audit-readiness plan. Use for compliance gap analysis,
Claude Code
$ npx -y skills add jassics/awesome-claude-security --skill compliance-assessment --agent claude-code
Codex
$ npx skills add jassics/awesome-claude-security --skill compliance-assessment -a codex -y
Cursor
$ npx skills add jassics/awesome-claude-security --skill compliance-assessment -a cursor -y
Gemini CLI
$ npx skills add jassics/awesome-claude-security --skill compliance-assessment -a gemini-cli -y
GitHub Copilot
$ npx skills add jassics/awesome-claude-security --skill compliance-assessment -a github-copilot -y
OpenCode
$ npx skills add jassics/awesome-claude-security --skill compliance-assessment -a opencode -y
Windsurf
$ npx skills add jassics/awesome-claude-security --skill compliance-assessment -a windsurf -y
name: compliance-assessment description: >- Gap-assess an organization or system against a compliance framework (SOC 2, ISO 27001, PCI DSS, HIPAA, GDPR, NIST CSF/800-53), mapping controls to evidence, identifying gaps, and producing a prioritized remediation and audit-readiness plan. Use for compliance gap analysis, certification prep, or audit readiness.
A clear picture of where the org stands against the chosen framework: which controls are met, partial, or missing; the evidence for each; and a prioritized path to compliant + audit-ready.
1. **Scope & framework** — pick the framework(s) and define scope (systems, data, business units, the audit boundary). See `reference.md` for a per-framework map. 2. **Map controls** — enumerate the framework's controls/requirements; map each to the org's existing controls and the **evidence** that demonstrates it (policy, config, logs, tickets, attestations). 3. **Assess each control** — Met / Partial / Not met, with the evidence or the gap. Be honest; reuse outputs from the operational plugins as technical evidence (e.g. `cloud-security`, `sast-sca`, `detection-engineering`). 4. **Identify gaps & risk** — for each gap, the control intent, the exposure it leaves (link `risk-assessment`), and the effort to close. 5. **Prioritize remediation** — by risk and by audit deadline; assign owners and target dates. 6. **Audit readiness** — organize evidence, dry-run control testing, and a remediation tracker an auditor can follow.
A compliance gap analysis: control · requirement · status · evidence · gap · owner · priority · target date, plus a remediation roadmap and an evidence index. Use `security-reporting`; visualize control coverage with `security-diagramming`.
Compliance ≠ security, but done well it raises the floor — map controls to *real* evidence, not aspirational policy. Many frameworks overlap heavily (ISO 27001, SOC 2, NIST); assess once and map to several to avoid duplicate work. Verify the current version of each framework. Track gaps with owners and dates — an audit is a deadline.
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.
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity,…
Test the agent execution harness/runtime itself — LangChain/LangGraph, AutoGen, CrewAI, custom ReAct-style loops, or…
Assess an autonomous / tool-using AI agent for security end-to-end: tool privileges, autonomy and approval boundaries, excessive…
Test what an AI agent will actually do without human confirmation, including under injected-goal / prompt-injection scenarios, to…
Review the security of MCP (Model Context Protocol) servers/clients an agent uses: server trust tier, tool/resource description…
Inventory the tools/functions an AI agent can call and audit their privileges, side effects, and approval requirements to find…
Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication,…
Extract and decrypt Windows DPAPI-protected secrets (Credential Manager, browser logins/cookies, Wi-Fi credentials, KeePass keys)…
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting…