{"candidate_reason": "prompt scope discovery", "chunk_end": 175, "chunk_start": 1, "chunk_summary": "The prompt defines complex logic for visual continuity and reference usage, but relies on overloaded semantic channels, brittle keyword-based exclusion lists for validation, and contains scenario-specific pollution in examples.", "duration_ms": 27524, "findings": [{"category": "semantic_string_judgment", "evidence": "staging.gaze_target 기반 immobilized mode 산출", "line_end": 68, "line_start": 68, "recommended_fix": "Introduce a dedicated physical_state or mobility_status field in the schema instead of inferring state from gaze targets.", "severity": "P1", "why_problematic": "The gaze_target field is being overloaded to carry physical state information (immobilized mode). This is a brittle semantic channel where a field named for one purpose (gaze) is used to infer a completely different physical state for prompt sanitization."}, {"category": "llm_closed_list_instruction", "evidence": "human / person / character / body / figure / man / woman / detective / prisoner / child / person silhouette", "line_end": 157, "line_start": 156, "recommended_fix": "Use a structured entity_type enum (e.g., PERSON, PROP, ENVIRONMENT) and have the LLM categorize entities rather than relying on keyword exclusion in natural language labels.", "severity": "P1", "why_problematic": "This is a closed list of phrases used as a semantic classifier to define what constitutes a 'person' for the purpose of fail-fast validation. It forces the LLM to match open-world descriptions against a brittle list to enforce a non-person constraint on labels."}, {"category": "schema_or_enum_drift", "evidence": "immobilized_character / character / pose 등 enum 외 값 절대 금지", "line_end": 161, "line_start": 161, "recommended_fix": "Ensure the kind enum is centrally defined in the SOT schema and shared across all pipeline steps to prevent drift.", "severity": "P2", "why_problematic": "The prompt explicitly lists forbidden enum values that likely exist in other parts of the pipeline or previous versions, indicating that the 'kind' field's enum is not centrally enforced or synchronized."}, {"category": "scenario_dependent_prompt", "evidence": "the same small reddish mark on the wrist", "line_end": 169, "line_start": 169, "recommended_fix": "Replace specific scenario details with generic placeholders like 'a unique texture detail' or 'a specific marking on the object'.", "severity": "P2", "why_problematic": "This is a highly specific visual detail (a 'reddish mark on the wrist') used as a concrete example. Such specific scenario-dependent props can bias the LLM towards forensic or injury-related scenarios in arbitrary future generations."}], "path": "prompts/_base/shot_dependency_t2i/7.202605151200/system.md", "scan_kind": "prompt", "sha256": "4bb9564d103d4c10a4183bbc190f58568e1564cf199cf2e4defb057a3542b378"}