twitter-reader

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and ingests public, user-generated Twitter/X content via the jina.ai proxy (see SKILL.md and the scripts/fetch_tweet.py and scripts/fetch_tweets.sh which call https://r.jina.ai/<tweet_url>), so untrusted third-party post content is read and used by the agent and could contain instructions that influence its actions.