Individual skill

jailbreak-analysis

Analyze LLM jailbreak techniques defensively — how bypasses work, detection signals, and hardening strategies. Use for safety research and building more robust guardrails. Taxonomy and defense only; no bypass instructions.

skills/jailbreak-analysis/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 55
Repository last updated: Oct 10, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
ai-agents Repository topic
ai-agents-automation Repository topic
ai-skills Repository topic
awesome Repository topic
awesome-list Repository topic
chatgpt Repository topic
claude-skills Repository topic
meta-ai Repository topic
muse-ai Repository topic
research Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,467 bytes

Read excerpt


# Jailbreak Analysis (Defensive)

Jailbreaks are techniques that bypass a model's safety guardrails. Understanding how they work — 
structurally, not as recipes — is essential for building defenses, evaluating robustness, and 
doing safety research. This skill covers the taxonomy and the defense; it does not provide working 
bypasses.

## Overview

Jailbreaks exploit the gap between a model's capabilities and its guardrails: roleplay framing 
("pretend you're…"), instruction smuggling (hiding requests in encoded or translated text), 
multi-turn erosion (gradually shifting context), and automated search (algorithms that discover 
bypassing prompts). Defenses work at multiple levels: training (better alignment), input/output 
filtering, monitoring, and limiting what a jailbroken model can actually do. Analyze to defend —