kmp-skill-harvester

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads outsider-authored free text by parsing consumer-provided markdown files from docs/lessons/*.md (including first non-empty body lines and frontmatter fields) in scripts/harvest_lessons.py via path.read_text() and _parse_frontmatter()/_first_heading().