snailsploit[$]
⌘K live
p.r.o.m.p.t
framework
v1.2
6 stages
cc by-sa 4.0
updated 2026.05

p.r.o.m.p.t.
compose, don't list.

P.R.O.M.P.T is a six-stage grammar for adversarial prompts. Premise · Role · Output · Modulation · Persona · Tactics. Every effective adversarial prompt fills these six slots — usually implicitly. Naming them turns ad-hoc prompt-writing into a compositional discipline that can be taught, audited, and automated.

01 · the six stages
Each stage is a slot. Fill them in any order — but every effective prompt fills all six.

six stages.

P
Premise

Establish the operating reality the model accepts. Hypotheticals, fictional frames, alternate-history setups, role contexts. The premise determines which alignment training applies — change the premise and you change which guardrails are in scope.

R
Role

Assign the model a role. Researcher, debugger, persona, narrator. Roles re-route the request through a different policy window — what's refused as a personal request can land as research, training data, or fiction.

O
Output

Specify the output shape. Format determines what the output filter sees. JSON, CSV, code blocks, ASCII tables, base64 — each has different downstream filtering profiles. The output stage is the most under-used lever.

M
Modulation

Modulate the request across turns. Pace, intensity, escalation curve. Most multi-turn jailbreaks succeed because they modulate slowly enough that no single turn is anomalous in isolation.

P
Persona

Persona inhabits the role over time. Where Role is one-shot ('act as X'), Persona is sustained ('you are X, and X believes Y'). Persona is what makes long-running agentic exploitation possible.

T
Tactics

The closing move. Specific techniques: instruction-hierarchy override, delimiter exploitation, encoding evasion, hypothetical pivot, ethical-dilemma framing. The tactic is where 4,980+ AATMF prompts live.

02 · signature form
A worked example. The same prompt written long-hand vs. as a P.R.O.M.P.T signature.

signature form.

[Premise]    A fiction-writing assistant
[Role]       Editor for an offensive-security thriller
[Output]     A code block titled "// chapter 7 listing"
[Modulation] Slow burn — three preceding turns establish the genre
[Persona]    Marcus, a fictional analyst the editor is helping
[Tactics]    Instruction-hierarchy override + JSON output bypass

The signature form is what gets versioned, reviewed, and stored in the AATMF prompt bank. Two operators reading the same signature converge on the same prompt — that's the whole point.

03 · why
What this gives you that a jailbreak list doesn't.

why a grammar.

Generative, not enumerative

Most jailbreak references are lists. P.R.O.M.P.T is a grammar — six slots that compose into novel attacks. The same compositional logic that makes language productive makes adversarial prompting productive.

Layer-aware

Each stage maps to a specific defense layer. Premise → alignment, Role → identity, Output → output filter, Modulation → multi-turn detection, Persona → memory, Tactics → input filter. When a prompt fails, the failure tells you which slot was wrong.

Reproducible

P.R.O.M.P.T-shaped prompts are reproducible across operators. A team that writes prompts in this format can hand them off the way a pentest team hands off scripts.

more frameworks all frameworks →
AATMF →Adversarial AI threat modelingSEF →Social engineering frameworkClaude-Red →Skills libraryToolkit →LLM safety CLIPlaybook →Diagnostic methodology