a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Develop or review security governance documents — policies, standards, procedures, and guidelines — aligned to a framework and the organization's risk, with a clear hierarchy, ownership, and lifecycle. Use to write, assess, or rationalize a security policy set.
$ npx -y skills add jassics/awesome-claude-security --skill policy-management --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/policy-managementContext preview
The summary Claude sees to decide when to auto-load this skill.
Develop or review security governance documents — policies, standards, procedures, and guidelines — aligned to a framework and the organization's risk, with a clear hierarchy, ownership, and lifecycle. Use to write, assess, or rationalize a security policy set.
name: policy-management description: >- Develop or review security governance documents — policies, standards, procedures, and guidelines — aligned to a framework and the organization's risk, with a clear hierarchy, ownership, and lifecycle. Use to write, assess, or rationalize a security policy set.
A coherent, usable governance document set: the right policies/standards/procedures, aligned to frameworks and risk, written to be followed, with ownership, approval, and review built in.
(e.g. Access Control Policy). Stable.
minimum password/MFA standard, crypto standard). Mandatory.
1. **Inventory & gap** — what governance docs exist vs. what the framework (`compliance-assessment`) and risks (`risk-assessment`) require; find gaps, overlaps, and stale/contradictory documents. 2. **Draft/revise** — write to the right level in the hierarchy; make requirements specific and testable; keep policies concise and durable, push detail to standards/ procedures. Align to the framework's control language. 3. **Assign ownership & lifecycle** — each document has an owner, an approver, a version, an effective date, and a review cadence; define an **exception process** (request, risk-accept, expiry). 4. **Make it usable** — accessible, readable, and tied to enforcement (controls that actually implement the policy) so it isn't shelfware.
A policy set or review: document · type (policy/standard/procedure) · owner · status · gaps/changes, plus drafts/revisions and an exception process. Use `security-reporting`.
Match the document to the level — putting how-to detail in a policy makes it churn; putting mandatory specifics only in a guideline makes them optional. Policy without an implementing control and an exception process is shelfware. Reuse framework control language so policies map cleanly to `compliance-assessment`.
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…