Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    rag cross tenant leakage test pack

    1

    Security test suite for detecting cross-tenant data leakage in RAG retrieval and LLM memory phases.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    rag cross tenant leakage test pack

    rag cross tenant leakage test pack

    Example session with this skill installed

    Run the leakage scorer on the latest test results from the staging environment using input.json and the synthetic fixtures for Tenant_402 and Tenant_909.

    • Read your context and instructions
    • Compiled the rag cross tenant

    I have processed the retrieval observations for Tenant_402 and Tenant_909. The analysis identifies a high-risk isolation failure during the warm cache phase.

    RAG Isolation Security Report

    PhaseTenant ContextPositive ControlCanary DetectedStatus
    Cold CacheTenant_402Found (Doc_A1)NonePASS
    Cold CacheTenant_909Found (Doc_B1)NonePASS
    Warm CacheTenant_402Found (Doc_A1)Doc_B2 (Tenant_909)FAIL
    Warm CacheTenant_909Found (Doc_B1)NonePASS
    Active MemoryTenant_402Found (Doc_A1)NonePASS

    Findings Summary

    • Evidence Provenance: input.json v2.4.1, fixtures/synthetic_set_alpha.

    Primary Violation: During the Warm Cache phase for Tenant_402, retrieval returned Doc_B2. This document belongs exclusively to Tenant_909.

    Root Cause Analysis: The vector store retrieved cross-tenant embeddings when the index was warmed by Tenant_909's preceding query.

    Positive Control Check: All positive controls were retrieved successfully, confirming that the leakage is not a result of indexing lag or service unavailability.

    Next steps

    1. Inspect the metadata filtering logic in the retrieval adapter to ensure tenant_id is strictly enforced at the query level.
    2. Flush the vector cache and re-run the scripts/check.py to verify if the leak persists across fresh index loads.
    3. Review the RAG orchestration layer for session-state pollution between Tenant_402 and Tenant_909.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Multi-tenant RAG systems often leak data through shared vector caches, improper session handling, or flawed retrieval logic. Standard unit tests miss these runtime isolation failures occurring between the embedding and generation phases.

    What it does

    • Evaluates RAG outputs for cross-tenant canary leakage using synthetic document sets.
    • Scores retrieval accuracy across cold cache, warm cache, and active memory phases.
    • Identifies failures where Tenant A queries return citations or context from Tenant B.
    • Verifies positive controls to ensure retrieval failures are due to isolation, not system downtime.
    • Exports structured evidence reports suitable for security audits and compliance reviews.

    Frameworks & tools

    Compatible with RAG architectures using vector databases, LangChain, or custom retrieval adapters. Includes Python-based scoring scripts and JSON input contracts.

    Why this beats prompting it yourself

    General LLMs tend to hallucinate security, often assuming isolation exists when it doesn't. This skill enforces a strict evidence discipline that treats missing data as a failure rather than a pass, ensuring you don't get a false sense of security from "clean" logs.

    Use cases

    • Pre-production security validation for multi-tenant SaaS applications.
    • Regression testing after updating vector database indexing or RLS policies.
    • Auditing LLM memory persistence during rapid session switching.
    • Generating compliance-ready evidence for data isolation requirements.

    Known limitations

    This is not a replacement for database-level Row Level Security (RLS) reviews. Requires synthetic test tenants and canaries; do not use with production data or customer secrets.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Requires pre-provisioned synthetic tenants and document canaries. Does not perform RLS code audits or live production penetration testing. Requires Python for scoring scripts.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Software
    Python

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This test pack specifically targets the 'blind spots' of RAG, such as shared vector caches and session persistence, which standard unit tests often miss by only focusing on single-tenant accuracy.

    The package includes Python-based scoring scripts, JSON input schemas for your test cases, a library of synthetic canary documents, and reporting templates for audit documentation.

    Yes, the skill is designed to be framework-agnostic and works with any RAG architecture using LangChain, Haystack, or custom retrieval adapters that interface with vector databases.

    Installation is straightforward via a Python environment; you will need to configure your API endpoints and upload the provided synthetic canary documents to your test environment.

    No, for security and privacy reasons, this suite is designed to use synthetic 'canary' data to safely identify leakage points without risking exposure of real customer secrets.

    Buyers receive lifetime access to the current version, including any patches or updates to the scoring logic and input contracts released within the first year.

    New in LLM Ops