x-blogger-analyzer

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 tweets from X/Twitter (e.g., via scripts/fetch_tweets.py that scrapes https://x.com/{username} and by asking users to paste copied tweets), so the agent will read untrusted third-party content that could carry indirect prompt injections.