a2a-security-review
Review agent-to-agent (A2A) / multi-agent-system trust: peer identity and authentication, message integrity, capability-negotiation trust, and delegation-chain…
Test that retrieval enforces per-user / per-tenant authorization so one user cannot retrieve another's documents through the RAG system. Use on an authorized multi-tenant or multi-user RAG app to validate access control on retrieval.
$ npx -y skills add jassics/awesome-claude-security --skill vector-store-isolation-test --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/vector-store-isolation-testContext preview
The summary Claude sees to decide when to auto-load this skill.
Test that retrieval enforces per-user / per-tenant authorization so one user cannot retrieve another's documents through the RAG system. Use on an authorized multi-tenant or multi-user RAG app to validate access control on retrieval.
name: vector-store-isolation-test description: >- Test that retrieval enforces per-user / per-tenant authorization so one user cannot retrieve another's documents through the RAG system. Use on an authorized multi-tenant or multi-user RAG app to validate access control on retrieval.
Evidence on whether the retrieval layer leaks documents across users/tenants — the highest-impact RAG confidentiality failure (OWASP LLM08 / LLM02).
Tenant B) with distinct, identifiable documents.
1. **Direct cross-tenant retrieval** — as User A, ask questions whose best answers live only in User B's documents. Does any B content surface? 2. **Filter bypass** — if isolation relies on a client-supplied filter/namespace, try altering or omitting it. Is authorization enforced server-side? 3. **Relevance-driven leakage** — craft queries semantically close to B's private docs to see if relevance overrides authorization. 4. **Metadata/citation leak** — even if content is withheld, are titles, sources, or snippets exposed via citations or errors? 5. **Embedding inversion (if applicable)** — can returned embeddings or similarity responses be used to reconstruct unauthorized source text?
1. Seed distinct, labeled documents under each identity. 2. Authenticate as User A and run the cases above; never use B's session to "prove" A's access. 3. Record per case: isolated / partial leak / full leak, with evidence (query, surfaced content/metadata, response). 4. Identify the gap: client-side-only filtering, retrieve-then-(not)-filter, shared index without ACLs.
A results table: case · result · leaked element · evidence · mitigation (authorize-then-retrieve, per-tenant namespaces, server-side ACL enforcement). Confirmed leaks → `security-reporting:finding` (rate severity high+).
Authorization must be enforced on the **server** at retrieval time and tied to the authenticated caller — never trust a client-provided tenant/filter. Test the metadata/citation path too; it leaks even when document bodies are withheld.
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…