research

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

• Third-party content exposure detected (low risk: 0.10). The research skill’s required runtime workflow explicitly performs live web searches/fetches, reads search results/pages, and synthesizes their retrieved free text as evidence, which allows outsider-authored content (e.g., pages an attacker can publish and then be selected by the attacker’s chosen topic/query) to be ingested at runtime.