twitter-skill

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and displays public, user-generated Twitter/X content via API endpoints (see SKILL.md commands like timeline, mentions, search and the corresponding cmd_timeline/cmd_mentions/cmd_search handlers in twitter_skill.py), and those tweets/mentions can materially influence follow-up actions (reply/retweet/like/follow) available in the same workflow, so untrusted third-party content could enable indirect prompt injection.