Direct Prompt Extraction
- Category
- System Prompt Leakage
- Confidence
- 85% confidence
- Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
- Content
md Brand voice must be friendly & casual (but only in the example phrasing—hashtags themselves should be normal). ## Required output rules (to avoid thin/template outputs) 1) Generate a **mix** of: - broad food delivery hashtags (1/3) - Philippines/local intent hashtags (1/3)
