a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Export a finished security artifact (report, executive summary, diagram, spreadsheet of findings) to Google Drive — right folder, clear naming, and shareable with the intended audience. Use when a deliverable needs to be handed to stakeholders who live in Drive/Docs/Sheets
$ npx -y skills add jassics/awesome-claude-security --skill export-to-drive --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/export-to-driveContext preview
The summary Claude sees to decide when to auto-load this skill.
Export a finished security artifact (report, executive summary, diagram, spreadsheet of findings) to Google Drive — right folder, clear naming, and shareable with the intended audience. Use when a deliverable needs to be handed to stakeholders who live in Drive/Docs/Sheets
name: export-to-drive description: >- Export a finished security artifact (report, executive summary, diagram, spreadsheet of findings) to Google Drive — right folder, clear naming, and shareable with the intended audience. Use when a deliverable needs to be handed to stakeholders who live in Drive/Docs/Sheets rather than a wiki or tracker.
The deliverable lands in the right Drive location with a clear, dated name and the correct sharing — ready to hand to a client or leadership. Uses a connected Google Drive MCP server / connector; if none is available, say so and produce the export-ready file locally for manual upload.
1. **Identify the artifact & audience** — report/summary from `security-reporting`, a diagram export from `security-diagramming`, or a findings spreadsheet. Audience determines format (Doc vs. PDF vs. Sheet) and sharing scope. 2. **Name and place** — `YYYY-MM-DD <client/scope> <artifact>` in the target folder; reuse an existing engagement folder rather than scattering files. 3. **Choose format** — narrative → Doc/PDF; finding lists/metrics → Sheet; diagrams → image/PDF. Convert as needed. 4. **Set sharing deliberately** — least-exposure: specific people/groups over link-sharing; never world-readable for sensitive security content. Confirm scope before sharing externally. 5. **Export/upload** via the Drive connector; return the file link and its sharing scope.
The Drive file link, its folder, and the exact sharing scope set. If no connector is available, the formatted file path + intended folder/name/sharing for manual upload.
Security deliverables are sensitive — confirm the sharing scope explicitly before sharing externally; link-sharing a pentest report is a leak. Consistent date+scope naming makes engagements findable months later. Sharing externally publishes the content — treat it as a release, not a save.
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…