semantic-view-patterns

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the ai_metadata snippet’s AI_SQL_GENERATION / AI_QUESTION_CATEGORIZATION blocks, which are designed to steer Cortex Analyst’s LLM using the user’s natural-language question at runtime (outsider-authored input).

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)