Vague Triggers
High
- Confidence
- 94% confidence
- Finding
- The trigger list includes very broad terms like 'bullshit', 'statistics', 'critical thinking', and 'fake news', which are common in ordinary conversation and can cause the skill to activate outside the user’s intent. This creates prompt-scope hijacking risk: the assistant may inject this skill’s instructions, onboarding, and formatting into unrelated conversations, degrading reliability and potentially overriding more appropriate system behavior.
