data-cleaning-and-visualization

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

• Third-party content exposure detected (high risk: 0.70). This skill's core workflow explicitly auto-scans and ingests files from external data directories (notably "crawled_data/" and "problem_files/") as stated in SKILL.md and implemented in scripts/clean_data.py, so it processes untrusted/scraped third-party content that can affect cleaning, visualization, and downstream steps.