product-manager-toolkit

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can be ingested when the required runtime workflow runs scripts/customer_interview_analyzer.py on a user-supplied transcript file, which is arbitrary text authored by someone other than the operating user (e.g., interviewee/customer notes) and is read via Path(args.transcript).read_text() into the LLM context.