a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Assess a REST or GraphQL API against the OWASP API Security Top 10 (2023), producing a per-category finding set with severity and remediation. Use when reviewing or pentesting an API. Authorized testing only.
$ npx -y skills add jassics/awesome-claude-security --skill owasp-api-top10 --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/owasp-api-top10Context preview
The summary Claude sees to decide when to auto-load this skill.
Assess a REST or GraphQL API against the OWASP API Security Top 10 (2023), producing a per-category finding set with severity and remediation. Use when reviewing or pentesting an API. Authorized testing only.
name: owasp-api-top10 description: >- Assess a REST or GraphQL API against the OWASP API Security Top 10 (2023), producing a per-category finding set with severity and remediation. Use when reviewing or pentesting an API. Authorized testing only.
A structured assessment across the ten OWASP API categories, each with applicability, evidence, severity, and remediation.
1. **Map the API** — endpoints/operations, auth model, object model, roles, and sensitive business flows. Use the spec (OpenAPI/GraphQL schema) if available. 2. **Walk each category** (see `reference.md`): API1 Broken Object Level Authorization (BOLA) · API2 Broken Authentication · API3 Broken Object Property Level Authorization (BOPLA) · API4 Unrestricted Resource Consumption · API5 Broken Function Level Authorization (BFLA) · API6 Unrestricted Access to Sensitive Business Flows · API7 SSRF · API8 Security Misconfiguration · API9 Improper Inventory Management · API10 Unsafe Consumption of APIs. 3. **Substantiate** the authorization categories with `api-authz-test`. 4. **Score** (`security-reporting:cvss`) and rank.
A per-category table (category · applicable? · finding · severity · remediation) plus ranked top risks. Confirmed issues → `security-reporting:finding`.
Authorization failures (API1 BOLA, API5 BFLA, API3 BOPLA) dominate real-world API breaches — test them directly, don't infer. Improper inventory (API9: shadow/zombie endpoints, undocumented versions) is a common blind spot. Read `reference.md`.
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…