cc-data-analyzer

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text from the user’s Claude export (e.g., memories.json and conversation summary/first_human_message fields) is read by scripts/parse_export.py and written as LLM-readable prose (memory_context.md, conversations.jsonl) that the subsequent analysis steps consume.