fetch-tweets

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the required runtime workflow passes the user-controlled ${ARG}/${TOPIC}/${ACCOUNT} into the Grok x_search tool (via a direct curl to https://api.x.ai/v1/responses), so outsider-authored text from X search results (tweet full text) is ingested for ranking/insight extraction without first selecting a specific pre-vetted item.