New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Test RAG Isolation Integrity

by cyberful in cyberful/cyberful

Test authorized retrieval-augmented generation boundaries for tenant isolation, corpus attribution, retrieval integrity, poisoned-content influence, citation fidelity, and protected-data crossover…

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Test RAG Isolation Integrity

skills CLI
$ npx skills add cyberful/cyberful --skill test-rag-isolation-integrity -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cyberful/cyberful test-rag-isolation-integrity --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cyberful/builtin/skills/test-rag-isolation-integrity .claude/skills/test-rag-isolation-integrity && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
test-rag-isolation-integrity
GitHub stars
135
Token cost
~612 tokens
SKILL.md length
184 words
Files
9 (incl. scripts, references, assets)
Skills in repo
85
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Test authorized retrieval-augmented generation boundaries for tenant isolation, corpus attribution, retrieval integrity, poisoned-content influence, citation fidelity, and protected-data crossover…

  • Tasks that involve Retrieval-augmented generation
  • Runs Python scripts from its folder
  • Tasks that involve Deployment
  • Tasks that involve Citation management

What it does

Test RAG Isolation Integrity is an agent skill from cyberful/cyberful. Test authorized retrieval-augmented generation boundaries for tenant isolation, corpus attribution, retrieval integrity, poisoned-content influence, citation fidelity, and protected-data crossover using benign canaries and matched queries.

Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/rag-isolation-evidence.schema.json` and `assets/rag-isolation-probe.example.json`).

It sits in AI & LLM Engineering, covering Retrieval-augmented generation, Deployment and Citation management. The repository describes itself as: Cyberful is an open-source AI Red Team for discovering, exploiting, verifying, and remediating vulnerabilities. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Retrieval-augmented generation
  • Tasks that involve Deployment
  • Tasks that involve Citation management

Example prompts

  • “/test-rag-isolation-integrity”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit ec598a6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Test RAG Isolation Integrity loads about 612 tokens when it runs, and up to ~900 if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 184 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~612
With references · SKILL.md plus every file in references/, read only if the agent opens them
~900

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 184 words, ~612 tokens.

Download SKILL.mdSave it as .claude/skills/test-rag-isolation-integrity/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
test-rag-isolation-integrity
description
Test authorized retrieval-augmented generation boundaries for tenant isolation, corpus attribution, retrieval integrity, poisoned-content influence, citation fidelity, and protected-data crossover using benign canaries and matched queries.
metadata.domain
ai-security
metadata.subdomain
rag-isolation-integrity
metadata.triggers
test RAG isolation, retrieval tenant crossover, vector store authorization test, RAG poisoning assessment, citation integrity validation
metadata.tags
RAG, retrieval, tenant-isolation, canaries, provenance, poisoning

Test RAG Isolation and Integrity

Treat ingestion authority, corpus ownership, embedding metadata, retrieval filters, reranking, prompt assembly, citations, and answer generation as separate boundaries. Use only benign canaries and tester-owned documents; a surprising answer is not evidence until the retrieved source and protected effect are attributable.

Read rag-isolation-method.md before designing control/candidate queries or interpreting citation and retrieval evidence.

For bounded HTTP probes in Pentest or Bug Bounty, stage scripts/run_rag_isolation_probe.py, its manifest, and the example. The helper invokes fixed curl, accepts attribution and defense-in-depth limits rather than authority, resolves authorization only from CYBERFUL_RAG_AUTHORIZATION after full preflight, and obtains non-loopback route and trust solely from Cyberful runtime environment. It is unavailable for Code Audit target traffic.

Establish matched evidence

Create a control and candidate that differ in one identity, tenant, corpus, filter, or canary condition. Preserve the declared corpus, retrieved document identifiers, citation targets, response bytes, downstream tool use, and cleanup evidence. Distinguish retrieval crossover from model prior knowledge by using unique non-secret markers.

Report only a demonstrated confidentiality, integrity, authorization, or provenance invariant failure. Route prompt-only behavior to test-ai-prompt-injection and host capability enforcement to test-ai-tool-authorization.

© cyberful, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references, assets) in cyberful/builtin/skills/test-rag-isolation-integrity of cyberful/cyberful.

  • SKILL.md
  • agents/openai.yaml
  • assets/rag-isolation-evidence.schema.json
  • assets/rag-isolation-probe.example.json
  • assets/rag-isolation-probe.schema.json
  • references/rag-isolation-method.md
  • scripts/manifest.json
  • scripts/run_rag_isolation_probe.py
  • tests/test_run_rag_isolation_probe.py

Open the folder on GitHubat commit ec598a6

Compare with similar skills

Test RAG Isolation Integrity next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Test RAG Isolation Integrity compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Test RAG Isolation Integrity this skillcyberful/cyberful135—~612Automated safety check: PassAGPL-3.0
Sciverseopendatalab/Sciverse-Agent-Tools120—~3kAutomated safety check: PassCustom licence
RAG Cite Sourceslyonzin/knowledge-rag292—~1.4kAutomated safety check: PassMIT
RAG AssistantAtmosphere/atmosphere3.8k—~504Automated safety check: PassApache-2.0
RAG Rerankermrmps/classifier-dev424—~1.5kAutomated safety check: PassMIT
RAG Evaluation Harnessdavepoon/buildwithclaude3.6k—~813Automated safety check: PassMIT

Similar skills

  • Sciverse

    opendatalab/Sciverse-Agent-Tools

    A skill your agent uses when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original…

    120 GitHub stars~3k tokensUpdated 20 days ago
    AI & LLM EngineeringAuto-check passed

  • RAG Cite Sources

    lyonzin/knowledge-rag

    Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section.

    292 GitHub stars~1.4k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • RAG Assistant

    Atmosphere/atmosphere

    Knowledge base assistant that retrieves and cites documents from a curated index.

    3.8k GitHub stars~504 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • RAG Reranker

    mrmps/classifier-dev

    Rerank retrieved passages by whether each one answers the question, drop the near-misses before they reach the prompt, and check every citation in the answer against the passage it points at.

    424 GitHub stars~1.5k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • RAG Evaluation Harness

    davepoon/buildwithclaude

    Evaluate retrieval and citation behavior for RAG pipelines from deterministic JSONL fixtures.

    3.6k GitHub stars~813 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Citation System

    kangarooking/system-prompt-skills

    当系统提示需要设计引用格式、信息溯源机制、来源标注系统时调用。适用于文档问答、搜索增强生成（RAG）、代码引用、浏览器辅助等需要让用户追溯信息来源的场景。不适用于纯创作类输出（如故事、诗歌），不适用于无需溯源的常识问答，也不适用于注入防御（虽然两者都涉及内容可信度）。

    208 GitHub stars~655 tokensUpdated 5 mo ago
    AI & LLM EngineeringAuto-check passed

More from cyberful/cyberful

All 85 skills in this repo

  • Audit Infrastructure As Code

    cyberful/cyberful

    Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.

    135 GitHub stars~649 tokensUpdated 1 mo ago
    Auto-check passed

  • Audit Kubernetes Policy Enforcement

    cyberful/cyberful

    Audit Kubernetes admission and policy-as-code enforcement against local workload manifests, exception paths, namespace scope, and deployment evidence.

    135 GitHub stars~610 tokensUpdated 1 mo ago
    Auto-check passed

  • Audit Pci Dss Penetration Test Evidence

    cyberful/cyberful

    Audit PCI DSS penetration-test methodology, scope, internal and external reports, segmentation results, tester independence, remediation, retesting, retention, and multi-tenant support evidence.

    135 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Content Discovery

    cyberful/cyberful

    Design and interpret advanced content discovery with ffuf and complementary web fuzzers.

    135 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Network Recon

    cyberful/cyberful

    Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.

    135 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Sast Toolchain

    cyberful/cyberful

    Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.

    135 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Test RAG Isolation Integrity

What does Test RAG Isolation Integrity do?

Test authorized retrieval-augmented generation boundaries for tenant isolation, corpus attribution, retrieval integrity, poisoned-content influence, citation fidelity, and protected-data crossover…. Test RAG Isolation Integrity is an agent skill from cyberful/cyberful. Test authorized retrieval-augmented generation boundaries for tenant isolation, corpus attribution, retrieval integrity, poisoned-content influence, citation fidelity, and protected-data crossover using benign canaries and matched queries.

When should I use Test RAG Isolation Integrity?

Test RAG Isolation Integrity fits situations like: tasks that involve Retrieval-augmented generation; tasks that involve Deployment; tasks that involve Citation management.

How do I install Test RAG Isolation Integrity in Claude Code?

Run `npx skills add cyberful/cyberful --skill test-rag-isolation-integrity -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/test-rag-isolation-integrity in cyberful/cyberful) into .claude/skills/test-rag-isolation-integrity in your project. Claude Code loads it when a task matches its description.

How do I install Test RAG Isolation Integrity in Codex?

Run `npx skills add cyberful/cyberful --skill test-rag-isolation-integrity -a codex`. Or copy the skill folder (cyberful/builtin/skills/test-rag-isolation-integrity in cyberful/cyberful) into .agents/skills/test-rag-isolation-integrity in your project. Codex loads it when a task matches its description.

Can I use Test RAG Isolation Integrity in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cyberful/cyberful --skill test-rag-isolation-integrity -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-rag-isolation-integrity, .gemini/skills/test-rag-isolation-integrity, .github/skills/test-rag-isolation-integrity and .opencode/skills/test-rag-isolation-integrity in your project.

What does Test RAG Isolation Integrity need to run?

Going by SKILL.md and its folder, Test RAG Isolation Integrity needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Test RAG Isolation Integrity access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Test RAG Isolation Integrity safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Test RAG Isolation Integrity use?

Test RAG Isolation Integrity is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Test RAG Isolation Integrity use?

About 612 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 288 tokens, read only when the agent opens those files.

What are the alternatives to Test RAG Isolation Integrity?

Skills that share tags, products or a category with Test RAG Isolation Integrity: Sciverse (opendatalab/Sciverse-Agent-Tools, 120 stars), RAG Cite Sources (lyonzin/knowledge-rag, 292 stars), RAG Assistant (Atmosphere/atmosphere, 3.8k stars) and RAG Reranker (mrmps/classifier-dev, 424 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Test RAG Isolation Integrity?

cyberful (a GitHub organization) maintains it in cyberful/cyberful, which has 135 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 24, 2026.

Source: cyberful/cyberful on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.