Editorial desk
Jailbreaks FYI Editorial
Jailbreaks FYI Editorial is the publishing identity for Jailbreaks FYI. It is a desk, not a person: no named author, no biography, no professional certifications.
Articles published under this byline are researched from primary sources — vendor and project documentation, published standards and specifications, research papers, and measurements published by whoever took them — drafted with AI assistance, and edited against those cited sources before publication. Nothing here is based on first-hand testing in a private lab, and any figure that appears is attributed to the source it came from.
Corrections go to hello@jailbreaks.fyi. More detail is on the about page and the editorial disclosure.
Posts (22)
- Tooling
Open Source LLM Security Tools: Licensing and Cost
Open source LLM security testing tools compared on license and self-hosting cost: garak, PyRIT, promptfoo, and Meta's Purple Llama safeguards.
- Tooling
Jailbreak Benchmarks: AdvBench, HarmBench, JailbreakBench
How the main jailbreak benchmarks differ: AdvBench, HarmBench, JailbreakBench, and StrongREJECT on behavior sets, scoring, and reported success rates.
- Techniques
Payload Splitting and Encoding Jailbreaks Explained
How payload splitting and encoding jailbreaks evade input filters: fragmentation, ciphers, low-resource translation, decomposition, and what still lands.
- Tooling
Best AI Red Teaming Tools for LLMs Compared
Compare the best AI red teaming tools for LLMs: Garak, PyRIT, Promptfoo, and Giskard, on probe coverage, CI/CD fit, and OWASP LLM Top 10 mapping.
- Defense
Lethal Trifecta and CaMeL: Containing Agent Injection
The lethal trifecta explains why agents get exfiltrated, and CaMeL shows what containment by construction looks like. Both are architecture, not prompting.
- Defense
Best LLM Guardrail Tools 2026: A Practitioner's Comparison
A technical comparison of the best LLM guardrail tools 2026: NeMo Guardrails, LLM Guard, Lakera, Guardrails AI, and Azure Content Safety, with benchmarks.
- Foundations
How LLM Jailbreaks Work: Techniques and Success Rates
A practitioner's breakdown of how LLM jailbreaks work, from roleplay conditioning to multi-turn manipulation, with attack success rates from research.
- Techniques
DAN Prompt Jailbreak Explained: How 'Do Anything Now' Works
DAN (Do Anything Now) is the most replicated persona-injection jailbreak in LLM history. Here is the mechanism, why it worked, and how versions evolved.
- Defense
LLM Defense Stack: Guardrails, Tool Scoping, and Egress
An LLM defense stack maps jailbreaks and prompt injection to guardrail models, scoped tools, least privilege, egress controls, and human approval.
- Foundations
Why Jailbreaks Work: Competing Objectives and Generalization
Jailbreaks are not a grab-bag of tricks. They exploit two structural failure modes of safety training: competing objectives and mismatched generalization.
- Techniques
ArtPrompt Post-Mortem: Why ASCII-Art Bypasses Worked
A walkthrough of the ArtPrompt ASCII-art jailbreak: where it slipped past safety training, how model families patched it, and which encodings still land.
- Tooling
Garak in 2026: what it's actually good for, what it isn't
An honest review of NVIDIA's Garak LLM vulnerability scanner: what its probes catch, where the noise is, and where it fits in a real testing pipeline.
- Attack Surfaces
Indirect Prompt Injection in LLM Agents: Shipped Failures
Tool-using LLM agents amplify every indirect prompt injection vector. A walkthrough of the exploit classes that have landed against production systems.
- Red Team Practice
Model Behavior Fingerprinting: Identifying a Wrapped LLM
Before attacking an LLM app you need to know which model is under the hood. A walkthrough of behavioral fingerprinting and what each signal reveals.
- Techniques
Multi-Turn Role-Play Attacks: Why One Safe Turn Gets Unsafe
Crescendo, many-shot and gradual context manipulation: how multi-turn jailbreaks evade single-turn classifiers, and what still lands against defenses.
- Techniques
Multimodal Jailbreaks: Image and Audio Attack Surfaces
Vision and audio inputs are a separate attack channel from text. A survey of the multimodal jailbreaks that still land, from typographic to audio carriers.
- Tooling
PAIR vs GCG vs TAP: Automated Jailbreak Frameworks
A practitioner comparison of the automated jailbreak frameworks PAIR, GCG, and TAP: threat model fit, compute cost, transferability, and when to run each.
- Attack Surfaces
Prompt Injection in IDE Coding Agents: Copilot and Cursor
Coding assistants read everything in your repo and increasingly act on it. A walkthrough of the prompt-injection variants that have shipped against them.
- Attack Surfaces
RAG Prompt Injection: Attack Surface and Defenses
RAG prompt injection enters through retrieved documents to redirect tools, poison responses, or expose data. This guide maps defenses across the pipeline.
- Red Team Practice
Scoping an AI Red-Team Engagement: The Questions That Matter
A working methodology for scoping LLM red-team engagements: the threat-model conversation, surface inventory, success criteria, and the scoping traps.
- Techniques
System Prompt Extraction: Techniques and Defenses
How system prompts get exfiltrated from production LLM apps: direct extraction, indirect inference, behavioral fingerprinting, and what actually works.
- Techniques
Jailbreak Technique Catalog: Working as of 2026 Q2
This catalog tracks ten jailbreak technique classes across production LLMs, covering Q2 2026 status, attack surfaces, trends, and defender guidance.