a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Profile a threat actor or campaign — their TTPs (mapped to MITRE ATT&CK), targeting, tooling, infrastructure, and likely intent — to support threat-informed defense. Use to understand who might target you and how, and to prioritize defenses.
$ npx -y skills add jassics/awesome-claude-security --skill threat-actor-profiling --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/threat-actor-profilingContext preview
The summary Claude sees to decide when to auto-load this skill.
Profile a threat actor or campaign — their TTPs (mapped to MITRE ATT&CK), targeting, tooling, infrastructure, and likely intent — to support threat-informed defense. Use to understand who might target you and how, and to prioritize defenses.
name: threat-actor-profiling description: >- Profile a threat actor or campaign — their TTPs (mapped to MITRE ATT&CK), targeting, tooling, infrastructure, and likely intent — to support threat-informed defense. Use to understand who might target you and how, and to prioritize defenses.
An actor/campaign profile that informs defense: what they do (TTPs), who they target, how they operate, and what that means for your detection and control priorities.
1. **Identity & aliases** — actor/group names across vendors (naming differs); suspected motivation (espionage, financial, hacktivism) and sponsorship if assessed. 2. **Targeting** — sectors, geographies, and victimology; whether your org fits the pattern (relevance to *you* is the point). 3. **TTPs** — map observed behaviors to **MITRE ATT&CK** across the lifecycle (initial access → impact); note signature techniques and tooling/malware families. 4. **Infrastructure** — typical C2, hosting, domains/certs patterns (link via `ioc-enrichment`). 5. **Framing** — use the Diamond Model (adversary–capability–infrastructure–victim) and Kill Chain to structure the picture; note confidence and gaps.
1. Aggregate reporting and your own telemetry/incidents (`dfir`); reconcile aliases. 2. Build the ATT&CK technique set and tooling profile; assess confidence per claim. 3. Assess relevance to your environment and which of their TTPs you can/can't detect. 4. Translate to action: detection priorities (`detection-engineering:detection-coverage-review`) and control/hardening recommendations.
An actor profile: aliases · motivation · targeting · ATT&CK TTP set · tooling/ infrastructure · relevance-to-us · confidence/gaps · recommended detections & controls. Use `security-reporting`; visualize the ATT&CK profile with `security-diagramming`.
The deliverable isn't a biography — it's *what their TTPs mean for your defenses*. Reconcile vendor aliases (the same group has many names) and be explicit about confidence and intelligence gaps. Prioritize defending the techniques they actually use and that you currently can't detect.
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…