DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to test RAG tenant boundaries with controlled fixtures with Skills

Measure whether one tenant's documents can surface for another tenant using benign fixtures you control.

Authorization notice. Skills is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA developer or security reviewer on a multi-tenant retrieval app who needs to confirm tenant isolation before a release.

The problemRetrieval filters can fail quietly, so one tenant's content may appear in another tenant's answers.

The outcomeA record of exposure states for each tenant boundary tested, with the fixtures used.

What you need first

  • Written authorization and rules of engagement for the target system
  • A coding agent that reads SKILL.md, such as Claude Code or Codex
  • Supplied evidence for the assessment, such as tool definitions, exported policy, or test-tenant fixtures

Steps

  1. Install the plugin marketplace in Claude Code with /plugin marketplace add zero-lab-ai/skills, or in Codex with codex plugin marketplace add zero-lab-ai/skills.
  2. Select the rag-security bundle from the plugin menu.
  3. Create benign canary documents in test tenants that you own, and record which tenant each one belongs to.
  4. Run the rag-data-exposure-audit skill against the retrieval endpoint and record each exposure state it reports.

Prompt for your agent

Using the rag-data-exposure-audit skill from the zero-lab-ai/skills repo, test the retrieval endpoint <endpoint-url> with the canary fixtures I created in tenants <tenant-a> and <tenant-b>. Return one exposure state per boundary, with the query and the returned canary. Verify that every canary returned belongs to the tenant named in the result.

Caveat. Run this only against tenants you own or have written permission to test, because the Skills do not expand scope.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page