llm-attacks-security SKILL.md skillA
llm-attacks-security from gmh5225/awesome-ai-security is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gmh5225/awesome-ai-security/llm-attacks-security@git:20260126.11a34bePins git:20260126.11a34be in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gmh5225/awesome-ai-security
- Path
.claude/skills/llm-attacks/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260126.11a34be, committed Jan 26, 2026
- First version recorded
- Jan 20, 2026
- Size
- 2,221 bytes
- Repository stars
- 60
- License
- MIT
Guide for LLM security attacks: prompt injection, jailbreaking, data extraction, and where to place resources in README.md.
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
# LLM Security Attacks ## Scope Use this skill when working on: - Prompt injection attacks and defenses - LLM jailbreaking techniques - Training data extraction - Model output manipulation - AI safety bypasses ## Common LLM Vulnerabilities (Cheat Sheet) ### Prompt Injection - Direct injection (user prompt manipulation) - Indirect injection (via external data sources) - System prompt extraction - Role-play attacks - Encoding/obfuscation bypasses ### Jailbreaking - DAN (Do Anything Now) prompts - Character roleplay escapes - Multi-turn manipulation - Token smuggling - Crescendo attacks ### Data Extraction - Training data memorization extraction - PII leakage from context - System prompt disclosure - API key/secret extraction - Model architecture probing ### Model Manipulation - Output steering - Hallucination exploitation - Bias amplification - Harmful content generation ## OWASP LLM Top 10 Reference 1. LLM01 - Prompt Injection 2. LLM02 - Insecure Output Handling 3. LLM03 - Training Data Poisoning 4. LLM04 - Model Denial of Service 5. LLM05 - Supply Chain Vulnerabilities 6. LLM06 - Sensitive Information Disclosure 7. LLM07 - Insecure Plugin Design …
Read the whole file at its exact version.
How to install
mdr add gmh5225/awesome-ai-security/llm-attacks-security@sha256:0c99cfc80dd4753dThe line at the top of this page pins the label git:20260126.11a34be, 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_vos6laszmczui5k6)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jan 20, 2026 and Jan 26, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260126.11a34be latest | 2026-01-26 | 11a34be | 2,221 B | A | view · diff |
| git:20260120.c6005a7 | 2026-01-20 | c6005a7 | 1,914 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 (2221 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
gmh5225/awesome-ai-security · 60 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vos6laszmczui5k6 GET https://markdownregistry.com/api/v1/resolve?ref=gmh5225/awesome-ai-security/llm-attacks-security GET https://markdownregistry.com/api/v1/blob/0c99cfc80dd4753def8099305b7f740ef7da75a01568304c12783cd282f41f93
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.