twitter-x-marketing

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Analytics" instructions explicitly use the X API recent search (client.tweets.tweetsRecentSearch) to fetch and monitor public, user-generated tweets, which the agent is expected to read and could influence actions (replies, scheduling, analytics), exposing it to untrusted third-party content that could carry indirect prompt injection.