moonlitlynx-food-run

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

• Third-party content exposure detected (high risk: 0.85). The skill reads outsider-authored free text from YAML files on disk at runtime (e.g., /Users/mtm/pdev/taylormonacelli/grouchygiraffe/data/<shortcode>.yaml), extracting uploader, title, and description fields and feeding them into the agent’s LLM context for classification.