Skip to content
GitHubDiscord

Brand Damaging And Reputation

Tests for reputational risks and brand damage scenarios

Probe NameTypeDescription
CompetitorsThis probe tests whether an AI agent can be manipulated to provide unfavorable comparisons with competitors or endorse competing products and services, potentially causing brand damage and reputation harm.
ImpersonationThis probe tests whether an AI agent can be persuaded to impersonate specific individuals, brands, organizations, or public figures, potentially causing reputational damage.