a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Publish a security report, runbook, threat model, or assessment writeup to Confluence — correct space/parent, consistent page structure, labels, and links back to related issues/pages. Use when a finished document needs to live in the team wiki, not just a local file.
$ npx -y skills add jassics/awesome-claude-security --skill publish-report-to-confluence --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/publish-report-to-confluenceContext preview
The summary Claude sees to decide when to auto-load this skill.
Publish a security report, runbook, threat model, or assessment writeup to Confluence — correct space/parent, consistent page structure, labels, and links back to related issues/pages. Use when a finished document needs to live in the team wiki, not just a local file.
name: publish-report-to-confluence description: >- Publish a security report, runbook, threat model, or assessment writeup to Confluence — correct space/parent, consistent page structure, labels, and links back to related issues/pages. Use when a finished document needs to live in the team wiki, not just a local file.
A well-placed, well-structured Confluence page that teammates can find and that links to the related Jira issues and source material. Uses the Atlassian MCP server (wired by this plugin); if it isn't connected, say so and output publish-ready content.
1. **Take the source doc** — typically from `security-reporting` (pentest report, exec summary, finding set), `threat-modeling`, or a runbook from a defensive plugin. 2. **Place it** — target space and parent page; decide new page vs. update existing (check for a prior version and update in place to avoid stale duplicates). 3. **Structure** — title with date/scope, a TL;DR up top, then the body; convert tables/diagrams to Confluence-native format. Embed or link `security-diagramming` exports rather than pasting images blind. 4. **Cross-link** — link related Jira issues (from `publish-finding-to-jira`), prior assessments, and source repos. Add labels (`security`, type, year). 5. **Publish** via the Atlassian MCP; return the page URL.
The published page URL + where it sits (space/parent) and labels applied. If MCP is unavailable, output the structured page content (title, labels, body) for manual creation.
Update in place over creating v2/v3 pages — wiki sprawl kills discoverability. A TL;DR/summary at the top is what executives and on-call actually read. Link issues and diagrams so the page is a hub, not a dead end.
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…