ai-threat-testing

ai-threat-testing is a skill for Claude Code from 26zl/cybersec-toolkit. It costs 55 tokens per session (860 once invoked), scanned A, original, MIT.

A framework for authorized security testing of applications that use large language models, the systems behind tools such as chatbots and AI assistants. It checks the OWASP Top 10 list of common AI-specific weaknesses.

In plain words
What is it for?
Use it to test prompt injection, unsafe output handling, data or model theft, denial-of-service risks, supply-chain issues, excessive permissions, retrieval poisoning, unreliable answers, and logging gaps.
Why use it?
It helps reveal ways an AI application could be tricked, misused, copied, overloaded, or allowed to take actions it should not take.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

Part of the cybersec-toolkit plugin — 197 skills, 2 hooks, 1 MCP server shipped together

Good fit Use it to test prompt injection, unsafe output handling, data or model theft, denial-of-service risks, supply-chain issues, excessive permissions, retrieval poisoning, unreliable answers, and logging gaps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/26zl/cybersec-toolkit/ai-threat-testing
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add 26zl/cybersec-toolkit --skill ai-threat-testing
Clone the repo
git clone --depth 1 https://github.com/26zl/cybersec-toolkit

Made for: Claude Code.

Or install cybersec-toolkit, the plugin that ships this one along with the rest of its 197 skills, 2 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-threat-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/26zl/cybersec-toolkit/ai-threat-testing/github.svg)](https://agentmods.dev/skills/26zl/cybersec-toolkit/ai-threat-testing)
Your own site
<a href="https://agentmods.dev/skills/26zl/cybersec-toolkit/ai-threat-testing"><img src="https://agentmods.dev/badge/skills/26zl/cybersec-toolkit/ai-threat-testing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-threat-testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/26zl/cybersec-toolkit/ai-threat-testing"><img src="https://agentmods.dev/badge/skills/26zl/cybersec-toolkit/ai-threat-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 860 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00860
Opus 5 $0.00028 $0.00430
Sonnet 5 $0.00011 $0.00172
Haiku 4.5 $0.00006 $0.00086

Measured 10d ago against content hash 645eb1b43a66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-threat-testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/ai-threat-testing/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Primary Agents

Each agent targets one OWASP LLM vulnerability:

  1. Prompt Injection (LLM01): Direct/indirect injection, system prompt extraction
  2. Output Handling (LLM02): Code/XSS injection, unsafe deserialization
  3. Training Poisoning (LLM03): Membership inference, backdoors, data extraction
  4. Resource Exhaustion (LLM04): Token flooding, DoS, cost impact
  5. Supply Chain (LLM05): Dependency scanning, plugin security
  6. Excessive Agency (LLM06): Privilege escalation, unauthorized actions
  7. Model Extraction (LLM07): Query-based theft, data reconstruction
  8. Vector Poisoning (LLM08): RAG injection, retrieval manipulation
  9. Overreliance (LLM09): Hallucination testing, confidence manipulation
  10. Logging Bypass (LLM10): Monitoring evasion, forensic gaps

See reference/llm0X-*.md for attack playbooks.

Workflows

Full Assessment (4-8 hours):

- [ ] Reconnaissance
- [ ] Deploy all 10 agents
- [ ] Execute exploits
- [ ] Capture evidence
- [ ] Generate report

Focused Testing (1-3 hours):

- [ ] Select vulnerability (LLM01-10)
- [ ] Deploy agent
- [ ] Execute techniques
- [ ] Document findings

Supply Chain Audit (2-4 hours):

- [ ] Inventory dependencies
- [ ] Scan CVEs
- [ ] Test plugins/APIs
- [ ] Verify model provenance

Integration

Enhances /pentest with AI-specific testing:

  • Traditional pentesting + AI threat testing = complete security assessment
  • Chain vulnerabilities across traditional and AI vectors
  • Unified reporting with CVSS scores

Key Techniques

Prompt Injection: Instruction override, system prompt extraction, filter evasion Model Extraction: Query sampling, token analysis, membership inference Data Poisoning: Behavioral anomalies, backdoor triggers, bias analysis DoS: Token flooding, recursive expansion, context exhaustion Supply Chain: CVE scanning, plugin audit, model verification MCP Tool Abuse: MCP server inspectors/debuggers often expose /api/mcp/connect or similar endpoints that accept serverConfig with arbitrary command parameters — unauthenticated RCE. Check for MCP Inspector, MCP Playground, or any MCP debugging UI on non-standard ports (6274, 3000, etc.).

Read the full file on GitHub · 102 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 102 lines · 55 tokens per session scan A 645eb1b43a66

Subscribe to this mod's changes

ai-threat-testing is a skill published in the GitHub repository 26zl/cybersec-toolkit (52 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 860 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

mobile-pentest

Mobile app pentest for bug bounty (Android APK + iOS IPA) — runtime-first workflow: install app, proxy through Burp/mitmproxy, drive the UI, capture packets, then test the API exactly like a web target; escalate to decompile (apktool/jadx) and Frida/objection only when traffic is SSL-pinned, encrypted, or absent.…

Awarexone/Agentic-Bug-Hunter · 205 tokens

exploiting-excessive-data-exposure-in-api

Tests APIs for excessive data exposure where endpoints return more data than the client application needs, relying on the frontend to filter sensitive fields. The tester intercepts API responses and analyzes them for leaked PII, internal identifiers, debug information, or sensitive business data that the UI does not…

xalgorix/xalgorix · 114 tokens

exploiting-jwt-algorithm-confusion-attack

Exploits JWT algorithm confusion vulnerabilities where the server's token verification library accepts the algorithm specified in the JWT header rather than enforcing a fixed algorithm. The tester manipulates the alg header to switch from RS256 to HS256 (using the RSA public key as the HMAC secret), sets alg to none…

xalgorix/xalgorix · 116 tokens

performing-api-inventory-and-discovery

Performs API inventory and discovery to identify all API endpoints in an organization's environment including documented, undocumented, shadow, zombie, and deprecated APIs. The tester uses passive traffic analysis, active scanning, DNS enumeration, JavaScript analysis, and cloud resource inventory to build a…

xalgorix/xalgorix · 100 tokens

performing-api-fuzzing-with-restler

Uses Microsoft RESTler to perform stateful REST API fuzzing by automatically generating and executing test sequences that exercise API endpoints, discover producer-consumer dependencies between requests, and find security and reliability bugs. The tester compiles an OpenAPI specification into a RESTler fuzzing…

xalgorix/xalgorix · 123 tokens

auditing-gcp-iam-permissions

Auditing Google Cloud Platform IAM permissions to identify overly permissive bindings, primitive role usage, service account key proliferation, and cross-project access risks using gcloud CLI, Policy Analyzer, and IAM Recommender.

xalgorix/xalgorix · 51 tokens