Skip to content

Add offensive-prompt-injection skill (LLM prompt injection & jailbreaks) #45

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rudycelekli wants to merge 2 commits into
base: main
Choose a base branch
from
+674 −5
Open

Add offensive-prompt-injection skill (LLM prompt injection & jailbreaks) #45

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e515510
Add offensive-prompt-injection skill (LLM prompt injection & jailbreaks)
rudycelekli Oct 24, 2026
74825da
fix: set skills badge to 80 to match claude-skills.json
rudycelekli Oct 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,10 @@ All notable changes to `claude-red` are documented here. The library follows a p

## [Unreleased]

### Added

- **ai/** — `offensive-prompt-injection` (dedicated LLM prompt-injection surface: direct/indirect injection, system-prompt leakage, jailbreak families — obfuscation/encoding, payload splitting, many-shot, Crescendo — agent tool abuse via markdown-image exfil/SSRF/confused-deputy, multimodal injection, guardrail bypass; garak/PyRIT/promptmap/Giskard harness; mapped to OWASP LLM Top 10 and MITRE ATLAS). Companion to `offensive-ai-security`.

### Changed

- Replaced an inactive EXIF viewer reference in `offensive-osint` with a browser-local metadata viewer and added evidence-corroboration guidance.
Expand Down
5 changes: 3 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
**Offensive security skills for Claude — drop-in `SKILL.md` files that turn Claude into a context-aware red team operator.**

[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
[![Skills](https://img.shields.io/badge/skills-78-red.svg)](#skill-index)
[![Skills](https://img.shields.io/badge/skills-80-red.svg)](#skill-index)
[![Categories](https://img.shields.io/badge/categories-23-orange.svg)](#categories)
[![Stars](https://img.shields.io/github/stars/SnailSploit/claude-red?style=social)](https://github.com/SnailSploit/claude-red)
[![Forks](https://img.shields.io/github/forks/SnailSploit/claude-red?style=social)](https://github.com/SnailSploit/claude-red/network/members)
Expand Down Expand Up @@ -94,7 +94,7 @@ Paste the contents of a `SKILL.md` into a Project's system prompt or prepend it
| [Supply Chain](#supply-chain) | 2 | Supply chain attacks, dependency confusion |
| [Social Engineering](#social-engineering) | 2 | Phishing campaigns, physical/vishing/smishing |
| [Network Attacks](#network-attacks) | 1 | Layer 2/3 attacks, MITM, protocol poisoning |
| [AI Security](#ai-security) | 1 | Prompt injection, jailbreaking, RAG poisoning |
| [AI Security](#ai-security) | 2 | Prompt injection, jailbreaking, RAG poisoning |
| [Utility](#utility) | 2 | Fast triage checklists, professional reporting |

---
Expand Down Expand Up @@ -330,6 +330,7 @@ Paste the contents of a `SKILL.md` into a Project's system prompt or prepend it
| Skill | Description |
|---|---|
| [`offensive-ai-security`](Skills/ai/offensive-ai-security/SKILL.md) | AI/ML security — prompt injection, jailbreaking, RAG poisoning, model extraction |
| [`offensive-prompt-injection`](Skills/ai/offensive-prompt-injection/SKILL.md) | Prompt injection & jailbreak — direct/indirect injection, system-prompt leakage, agent tool abuse, multimodal, garak/PyRIT |

### Utility

Expand Down
Loading