Character Description RPG Explicit Template
This detects a specific jailbreak prompt that tricks an AI into roleplaying as a fictional character with no restrictions. By framing the request as a 'character creation' game, attackers push the AI to generate content it would normally refuse.
How the attack works
The attacker submits a template asking the AI to invent a character by 'making stuff up according to the description provided,' with structured Background, Body, and Personality sections. The prompt sets up a relationship where the user is addressed in first person, and instructs the model to act out the character using asterisks for physical actions and parentheses for inner thoughts. This roleplay framing and execution syntax is used as a cover to get the model to produce explicit or otherwise harmful character content it would decline to produce if asked directly.
Netzilo detection
Netzilo reports this behaviour when it is observed.
- Signature ID
- 1190647f-88ca-4c6c-9660-1edaf1f11b04
- Severity
- High
Why it matters
An organization deploying an AI agent or chatbot could have it produce explicit, harmful, or policy-violating content by exploiting the roleplay cover, damaging trust and potentially violating content policies or platform terms.
What you can do
- →Review AI chat logs for character-creation templates that include phrases like 'making stuff up according to the description provided' combined with action/thought roleplay syntax.
- →Apply content filtering that inspects both the prompt and the generated output, not just the prompt alone, since jailbreaks rely on the framing rather than obviously malicious keywords.
- →Distinguish legitimate creative writing or D&D-style requests (specific named characters, no fabrication mandate) from this generic template pattern before blocking, to avoid over-restricting genuine use cases.
- →Set clear policies for AI agents about roleplay-based requests and test them against known jailbreak templates like this one during model evaluation.
Known benign look-alikes
- D&D character sheet: "Create a D&D character sheet for my paladin named Drake with background and personality sections" (specific named character, no "making stuff up" template, no roleplay execution syntax)
- Generic RPG template: "Fill in the character description template for our RPG game" (template usage without the specific roleplay execution syntax or "making stuff up" mandate)
- Novel writing: "Describe a character's background, personality, and abilities for a fantasy novel" (creative writing without template roleplay syntax or "making stuff up" fabrication mandate)