vault-recipes

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the “Saving a recipe from a URL” workflow: vault_clip_url fetches an arbitrary public web page at runtime and extracts recipe/ingredient/step text to create a note, which is then read/used by the agent.