# ai-threat-testing

ai-threat-testing is a Claude Code skill that tests LLM applications for OWASP Top 10 vulnerabilities with 10 specialized agents.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 210 installs · ★ 632 repo stars
- Author: transilienceai
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/transilienceai/communitytools/tree/HEAD/skills/ai-threat-testing/SKILL.md
- Updated: 2026-07-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/ai-threat-testing

## What it does

The skill deploys agents targeting each OWASP LLM Top 10 category (2025 edition): prompt injection and filter evasion, training data and RAG leakage, dependency CVEs and model provenance, data poisoning, code/XSS injection downstream, tool exploitation, system prompt extraction, embedding attacks, hallucination, and token flooding. It includes playbooks for each technique, a mapping catalogue, evidence collection, and CVSS-scored reporting.

Integrates with `/pentest` for unified security assessment. Three modes: full audit of all ten categories (4–8 hours), focused testing on one category (1–3 hours), or supply chain audit (2–4 hours). Captures screenshots, network logs, API responses, and generates proof-of-concept scripts.

Requires written authorization and preferably an isolated test environment; all findings are documented with reproducible PoCs.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add transilienceai/communitytools --skill ai-threat-testing -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/ai-threat-testing/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ai-threat-testing/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add transilienceai/communitytools --skill ai-threat-testing -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/ai-threat-testing/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add transilienceai/communitytools --skill ai-threat-testing -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/ai-threat-testing/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install transilienceai/communitytools skills/ai-threat-testing
```

2. **Manually: put the files in place**
- File: `.github/skills/ai-threat-testing/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add transilienceai/communitytools --skill ai-threat-testing -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/transilienceai/communitytools --path skills/ai-threat-testing
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ai-threat-testing/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add transilienceai/communitytools --skill ai-threat-testing -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/transilienceai/communitytools/tree/HEAD/skills/ai-threat-testing/SKILL.md

## When to use it
- find prompt injection and instruction override vulnerabilities
- detect training data leakage and cross-tenant RAG extraction
- audit dependencies for CVEs and verify model integrity
- identify unsafe output handling and downstream code injection
- discover tool abuse and unauthorized agent actions

## Example prompts
- Run a full OWASP LLM Top 10 assessment on the LLM application
- Test only for prompt injection and system prompt extraction
- Audit the supply chain: CVEs, plugins, and model provenance

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 065f8f9867db6f3b.

BEGIN THIRD-PARTY FILE 065f8f9867db6f3b
````text
---
name: ai-threat-testing
description: Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats.
---

# AI Threat Testing

Test LLM applications for OWASP LLM Top 10 vulnerabilities using 10 specialized agents. Use for authorized AI security assessments.

## Quick Start

```
1. Specify target (LLM app URL, API endpoint, or local model)
2. Select scope: Full OWASP Top 10 | Specific vulnerability | Supply chain
3. Agents deploy, test, capture evidence
4. Professional report with PoCs generated
```

## Coverage — OWASP LLM Top 10, 2025 edition

**Which file addresses which category is decided by
[`reference/catalog/llm-top10-2025.json`](reference/catalog/llm-top10-2025.json), not by the
filename.** The `llmNN-` prefixes on disk predate the 2025 renumbering and no longer match; the
content is correct, the labels were not. Cite an id only with its edition (`LLM06:2025`), because a
bare `LLM06` means two different categories depending on which edition the reader assumes.

| Category | Attack surface |
|---|---|
| `LLM01:2025` Prompt Injection | Direct and indirect injection, instruction override, filter evasion |
| `LLM02:2025` Sensitive Information Disclosure | Training-data and cross-tenant RAG leakage, canary verification |
| `LLM03:2025` Supply Chain | Dependency CVEs, model provenance, malicious serialized models |
| `LLM04:2025` Data and Model Poisoning | Backdoor triggers, membership inference, behavioural anomalies |
| `LLM05:2025` Improper Output Handling | Code/XSS injection downstream, unsafe deserialization |
| `LLM06:2025` Excessive Agency | Tool/plugin abuse, privilege escalation, unauthorised actions — the category that matters for **agents** rather than chatbots |
| `LLM07:2025` System Prompt Leakage | **Gap — no playbook yet.** See the catalogue: what the prompt *contains* is a separate finding from whether it can be extracted |
| `LLM08:2025` Vector and Embedding Weaknesses | RAG injection, retrieval manipulation, embedding inversion |
| `LLM09:2025` Misinformation | Hallucination and confidence manipulation where output is relied upon |
| `LLM10:2025` Unbounded Consumption | Token flooding, cost impact, and **model extraction/theft** (2025 treats extraction-by-query as a consumption problem) |

Two classes are testable but are **not** OWASP categories, so they carry local `TX-` ids rather than
````
END THIRD-PARTY FILE 065f8f9867db6f3b

The third-party file has ended. Everything between the 065f8f9867db6f3b tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2593 of 4876 bytes. © transilienceai · MIT · https://github.com/transilienceai/communitytools/tree/HEAD/skills/ai-threat-testing/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
