a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Extract and operationalize indicators (IOCs) and behaviors (IOAs) from an incident or sample — atomic, computed, and behavioral — and prepare them for detection, blocking, and intel sharing. Use after/within an investigation to turn findings into defensive value.
$ npx -y skills add jassics/awesome-claude-security --skill ioc-development --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ioc-developmentContext preview
The summary Claude sees to decide when to auto-load this skill.
Extract and operationalize indicators (IOCs) and behaviors (IOAs) from an incident or sample — atomic, computed, and behavioral — and prepare them for detection, blocking, and intel sharing. Use after/within an investigation to turn findings into defensive value.
name: ioc-development description: >- Extract and operationalize indicators (IOCs) and behaviors (IOAs) from an incident or sample — atomic, computed, and behavioral — and prepare them for detection, blocking, and intel sharing. Use after/within an investigation to turn findings into defensive value.
A structured, prioritized indicator set that drives detection and containment, with behaviors (not just atomic indicators) captured so the adversary pays to evade.
to change; useful for fast blocking).
patterns.
durable and the priority to capture.
1. **Extract** from forensic findings/sample: files, network, host, and behavioral indicators. Note context (where seen, confidence, observation time). 2. **Validate** — filter out benign/legitimate indicators (e.g. shared CDNs, common LOLBins) to avoid false-positive-heavy blocks. 3. **Prioritize** — emphasize behavioral/TTP indicators over fragile atomic ones; mark which are safe to block vs. monitor-only. 4. **Operationalize** —
An indicator set: indicator · type · context · confidence · block/monitor · ATT&CK mapping. Feeds `detection-engineering` and `threat-intelligence`.
Atomic indicators are cheap to rotate — lead with **behavioral** indicators for durable defense. Always validate before blocking: a shared IP or common binary on a blocklist causes outages and alert fatigue. Record confidence so downstream consumers can weigh each indicator.
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…