searching-mlflow-docs

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

• Third-party content exposure detected (high risk: 0.85). The workflow’s runtime WebFetch step downloads outsider-authored public web content from https://mlflow.org/docs/latest/llms.txt (and then additional .md docs) and feeds that readable text into the agent’s LLM context, creating indirect prompt-injection exposure.