resolve-recipe-ingredient-link

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow reads outsider-authored free text from the user-provided recipe ingredient line (“Recipe ingredient line:\n{line}”) and also ranks/chooses from a candidate list derived from a vault enumeration, so an attacker can influence the LLM inputs via the unresolved wikilink/line they submit.