ai-threat-testing SKILL.md skillA
ai-threat-testing from 26zl/cybersec-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add 26zl/cybersec-toolkit/ai-threat-testing@git:20260614.1d959e6Pins git:20260614.1d959e6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- 26zl/cybersec-toolkit
- Path
.claude/skills/ai-threat-testing/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260614.1d959e6, committed Jun 14, 2026
- First version recorded
- Apr 30, 2026
- Size
- 3,718 bytes
- Repository stars
- 87
- License
- MIT
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 …
Read the whole file at its exact version.
How to install
mdr add 26zl/cybersec-toolkit/ai-threat-testing@sha256:645eb1b43a660087The line at the top of this page pins the label git:20260614.1d959e6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_beffixwrvmwexrur)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Apr 30, 2026 and Jun 14, 2026, about one every 45 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260614.1d959e6 latest | 2026-06-14 | 1d959e6 | 3,718 B | A | view · diff |
| git:20260430.9ae5eef | 2026-04-30 | 9ae5eef | 3,667 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3718 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
26zl/cybersec-toolkit · 87 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_beffixwrvmwexrur GET https://markdownregistry.com/api/v1/resolve?ref=26zl/cybersec-toolkit/ai-threat-testing GET https://markdownregistry.com/api/v1/blob/645eb1b43a660087fe0cf734d25e10150a50e10f038c4a99cf2931e94da6ac6c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.