going-viral

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md workflow explicitly pulls "20 viral references" from public X/Twitter via the GET /x/tweets/search?sort=top&min_faves=5000 endpoint (see "Typical flow" step 2 and "Endpoints used"), and those untrusted, user-generated tweets are read and used to shape drafting/scoring/optimization, so they could inject instructions that alter behavior.