twitter-reader

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches arbitrary user-generated Twitter/X posts via the jina.ai proxy (https://r.jina.ai/{url}) as implemented in scripts/fetch_tweet.py and scripts/fetch_tweets.sh, so the agent ingests and interprets untrusted social-media content that could contain indirect prompt injection.