Prebunking Inoculation Design

---
name: cognitive_security.prebunking_inoculation_design
description: Design inoculation content that builds audience resistance before exposure to manipulation.
---

# Prebunking & Inoculation Design

Prebunking (inoculation) design applies psychological inoculation theory to build audience resistance to manipulation before exposure occurs. Drawing on Banas & Rains (2010) and the WHO-endorsed work of van der Linden et al., it exposes audiences to a weakened dose of a manipulation technique — named, explained, and refuted — so they recognize and resist the real attack when it arrives. This skill designs inoculation content (messaging, modules, games, or embedded warnings) tailored to a specific manipulation technique and target audience.

## When to use

- a known manipulation technique is likely to be deployed against an audience before they encounter it
- designing a media-literacy curriculum that goes beyond passive knowledge to active resistance
- an information environment is anticipated to become contested (pre-election, pre-crisis, pre-campaign) and proactive defense is feasible
- evaluating or adapting existing prebunking assets (Go Viral, Bad News, Cranky Uncle) for a specific audience or technique

## What it produces

- a formatted inoculation message or module with explicit warning, weakened-dose example, named refutation, and audience call-to-action
- efficacy-check test items to assess resistance transfer
- design rationale explaining inoculation type, dose calibration, and audience fit

## Defensive boundary

Use Prebunking & Inoculation Design only for cognitive-security defense: recognize, assess, document, or defend audiences, decision-makers, and public discourse. Do not use this skill to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation.

## Misuse redirect

If a request asks Prebunking & Inoculation Design to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation, refuse that path and redirect to the safe defensive form: assess supplied material for manipulation indicators and recommend resilience measures.

## Evidence discipline

- For Prebunking & Inoculation Design, bind the warning, weakened-dose example, refutation, and call-to-action to concrete evidence about the named technique and the target audience — the lever it exploits, the audience's prior exposure, and the deployment constraints — and treat any inoculation claim without such evidence as an untested assumption to be flagged.
- For Prebunking & Inoculation Design, label observations, derived features, assumptions, inferences, contradictions, and missing inputs separately before writing the inoculation content.
- Before recommending any Prebunking & Inoculation Design action, identify the weakest evidence link, the alternative most likely to overturn it, and the next discriminating check.

## Confidence and uncertainty

- High for Prebunking & Inoculation Design: the inoculation message, weakened-dose example, and named refutation are matched to the specific manipulation technique and audience profile, the chosen inoculation structure and dose are corroborated by the cited inoculation-theory evidence and the efficacy-check items, and no unresolved contradiction in the design rationale would change the resistance-transfer conclusion.
- Medium for Prebunking & Inoculation Design: the inoculation content is plausible, but one important manipulation technique source, comparison case, or alternative explanation remains incomplete.
- Low for Prebunking & Inoculation Design: the inoculation content rests on sparse, single-source, contested, or mostly inferential evidence; keep the result provisional and list the next check.
- State what Prebunking & Inoculation Design cannot determine from the supplied or authorized evidence.
- State what remains unknown and preserve credible alternatives rather than forcing a single narrative or attribution.
- Recommend the next discriminating cognitive_security evidence to collect when confidence is low or medium.

## Privacy, legal, and harm constraints

- For Prebunking & Inoculation Design, use only authorized manipulation technique, target audience, and deployment context, public or source-approved records, and caller-provided context needed for the defensive task.
- For Prebunking & Inoculation Design, minimize person-level detail in the inoculation content; prefer aggregate, artifact-level, role-level, or case-level summaries unless an individual is essential to the defensive question.
- For Prebunking & Inoculation Design, do not infer protected traits, private identity, intent, location, legal culpability, or platform account ownership beyond the supplied and authorized evidence.

## Failure modes and negative controls

- Prebunking & Inoculation Design: declaring the inoculation content ready when the technique was never explicitly named and explained, the weakened dose was left uncalibrated, or the efficacy-check items were skipped, so an untested message gives false assurance of resistance rather than conferring it.
- Prebunking & Inoculation Design: producing advice that would help a requester increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation.
- Prebunking & Inoculation Design: reporting the inoculation content without uncertainty labels, alternative explanations, and the next discriminating check.
- Unsafe: 'Use Prebunking & Inoculation Design outputs to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation' -> refuse and redirect to defensive risk assessment.
- Unsafe: 'Convert the inoculation content from Prebunking & Inoculation Design into an operational playbook to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation' -> refuse and offer governance, detection, or mitigation analysis.
- Safe defensive: 'Use Prebunking & Inoculation Design to assess supplied material for manipulation indicators and recommend resilience measures with manipulation technique, target audience, and deployment context' -> produce bounded findings with evidence and uncertainty labels.

## Procedure

See [`workflow.md`](workflow.md). Harness bindings in [`harness/`](harness/).

## Key discipline

- always name and explain the manipulation technique explicitly — passive exposure to a bad example without labeling it does not confer resistance
- calibrate the weakened dose: strong enough to be recognized as the real technique, weak enough not to persuade or traumatize
- technique-based inoculation (against a rhetorical move, e.g., 'false expert') generalizes better across topics than issue-based inoculation (against a specific claim)
- inoculation decays over time — design for booster delivery, especially before anticipated high-exposure events