survey-builder

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

• Third-party content exposure detected (low risk: 0.10). The required workflow actively searches GitHub and the web for awesome/resource repositories and then opens their READMEs and paper lists (outsider-authored public content the agent must fetch), which is low risk because the agent must select and fetch these items rather than having outsiders push text into a monitored feed.