x-research

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md (via references/shared-contract.md and routes like references/organic-benchmark.md/references/audience-voice.md), the workflow ingests outsider-authored free text by collecting public X posts/replies based on user-supplied seeds (keywords/hashtags/accounts/URLs) and then extracting reply text from selected public threads.