thesourdoughjourney-method-check

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

• Third-party content exposure detected (high risk: 0.85). The skill’s REQUIRED workflow ingests the recipe either “as a URL to fetch or as pasted recipe text,” which is outsider-authored free text/content from arbitrary third parties at runtime (public web pages or user-pasted text not authored by the operating user) into the agent’s LLM context.